© 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. 40464
    Prev
    Next
    INDEX
    Explanations

    mentions of legal or regulatory authorities and processes

    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
    447
    +0.27
    1.3%
    481
    +0.11
    0.5%
    509
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.27
    0.16
    743
    +0.11
    0.08
    224
    +0.10
    0.13
    Negative Logits
    oken
    -0.61
    tein
    -0.61
    Py
    -0.60
    erto
    -0.60
    ezvous
    -0.56
    weak
    -0.56
    Temperature
    -0.55
    veh
    -0.55
    iq
    -0.55
     wont
    -0.54
    POSITIVE LOGITS
    DERR
    0.71
    è¦ļéĨĴ
    0.68
     undet
    0.67
     conclud
    0.67
    ¶ħ
    0.66
     unnoticed
    0.64
     censor
    0.63
     alike
    0.62
    Enlarge
    0.60
    usk
    0.60
    Activations Density 21.557%

    No Known Activations