© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 8588
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences and opinions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of opinion or judgment about situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    encies
    -0.82
    ulative
    -0.76
     foregoing
    -0.67
    ences
    -0.66
     belie
    -0.66
    atible
    -0.61
    rations
    -0.60
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.59
     COMPLE
    -0.58
    ently
    -0.57
    POSITIVE LOGITS
    audi
    0.83
     namely
    0.80
     Corpus
    0.76
     Nicaragua
    0.74
     Kendrick
    0.73
    gran
    0.69
     Qualcomm
    0.66
     MacArthur
    0.66
     Hiroshima
    0.65
    SELECT
    0.65
    Activations Density 0.795%

    No Known Activations