© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 36648
    Prev
    Next
    INDEX
    Explanations

    names of different companies, institutions, and locations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    218
    +0.10
    0.5%
    272
    +0.09
    0.4%
    515
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    425
    +0.10
    0.13
    556
    +0.09
    0.10
    206
    +0.09
    0.08
    Negative Logits
     CTR
    -0.64
    Reply
    -0.63
    ĵĺ
    -0.61
    achine
    -0.61
     Hemp
    -0.60
    rill
    -0.59
    uzz
    -0.58
    Ĥİ
    -0.58
    Ped
    -0.58
     turnaround
    -0.57
    POSITIVE LOGITS
     Territories
    0.86
     Territory
    0.80
     territories
    0.72
    dom
    0.68
     territory
    0.66
     realms
    0.65
     occup
    0.63
     liabilities
    0.61
    doms
    0.60
    controlled
    0.56
    Activations Density 11.630%

    No Known Activations