© 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. 12511
    Prev
    Next
    INDEX
    Explanations

    expressions related to completeness or certainty, often denoted by the symbol '%'

    oai_token-act-pair · gpt-3.5-turbo

    phrases and expressions related to percentages and quantification

    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
    EStream
    -0.86
    */(
    -0.71
    iden
    -0.70
    verett
    -0.69
    zek
    -0.69
    Īè
    -0.68
     behav
    -0.66
    otom
    -0.65
    pload
    -0.65
     behavi
    -0.65
    POSITIVE LOGITS
    heartedly
    0.91
    luster
    0.76
    production
    0.74
    ablishment
    0.74
    ascript
    0.73
    atinum
    0.70
    entimes
    0.69
    inline
    0.68
    stop
    0.67
    beta
    0.67
    Activations Density 0.039%

    No Known Activations