© 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. 45884
    Prev
    Next
    INDEX
    Explanations

    misleading or false information in text, including statements that are incorrect or fraudulent

    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
    +0.16
    0.9%
    746
    +0.10
    0.5%
    0
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    73
    +0.16
    0.07
    762
    +0.10
    0.14
    139
    +0.09
    0.07
    Negative Logits
    iments
    -0.80
    ĸļ
    -0.79
    iment
    -0.74
    oleon
    -0.69
    ista
    -0.63
    isms
    -0.60
    iens
    -0.59
    arya
    -0.58
    achine
    -0.57
    illas
    -0.57
    POSITIVE LOGITS
    named
    0.68
     inflated
    0.67
     priced
    0.67
     diagnosed
    0.66
    ãĤ©
    0.66
     unfocusedRange
    0.65
    label
    0.64
     accused
    0.62
    ball
    0.62
     accuse
    0.62
    Activations Density 7.534%

    No Known Activations