© 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. 4-RES-JB
    11. 380
    Prev
    Next
    INDEX
    Explanations

    characters or words related to the term "character"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "character" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĸ¹
    -0.81
    hower
    -0.74
    EMS
    -0.72
     Reloaded
    -0.71
    DERR
    -0.66
    algia
    -0.64
    ILS
    -0.63
     Ãľ
    -0.63
    Trend
    -0.62
    ĸļ
    -0.62
    POSITIVE LOGITS
    acters
    1.61
    itably
    1.02
    isma
    0.94
    NetMessage
    0.92
    inic
    0.89
    coal
    0.85
    itable
    0.84
    iac
    0.84
    vin
    0.83
    izard
    0.82
    Activations Density 0.010%

    No Known Activations