© 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. 34794
    Prev
    Next
    INDEX
    Explanations

    brand names and companies mentioned in advertisements

    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
    679
    +0.13
    0.7%
    639
    +0.09
    0.5%
    17
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    639
    +0.13
    0.08
    747
    +0.09
    0.04
    288
    +0.08
    0.16
    Negative Logits
    izers
    -0.62
    uckle
    -0.59
    izabeth
    -0.58
    kson
    -0.54
    isers
    -0.53
    opez
    -0.52
     Morrow
    -0.51
     waking
    -0.50
     Mead
    -0.50
    ologically
    -0.49
    POSITIVE LOGITS
    culosis
    0.81
    apore
    0.75
    eki
    0.68
    allery
    0.67
     Policy
    0.61
    arten
    0.59
     Advertisement
    0.59
     Intent
    0.58
     Terrorism
    0.57
    eer
    0.56
    Activations Density 5.323%

    No Known Activations