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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 45928
    Prev
    Next
    INDEX
    Explanations

    details related to political figures and events

    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
    578
    +0.10
    0.5%
    649
    +0.10
    0.5%
    314
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    578
    +0.10
    0.06
    284
    +0.10
    0.09
    746
    +0.10
    0.04
    Negative Logits
     Novel
    -0.60
     Pony
    -0.60
     Cipher
    -0.60
     Drift
    -0.59
     Aer
    -0.58
     Dance
    -0.58
    ETS
    -0.56
    puter
    -0.56
     Lys
    -0.56
     juggling
    -0.55
    POSITIVE LOGITS
    chard
    1.29
    nam
    1.21
    Else
    1.14
    ifice
    1.08
    acles
    1.06
    acle
    1.04
    nery
    1.02
    acular
    1.00
    chid
    1.00
    ific
    0.99
    Activations Density 3.665%

    No Known Activations