© 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. 1-RES-JB
    11. 3323
    Prev
    Next
    INDEX
    Explanations

    phrases related to searching or investigating

    oai_token-act-pair · gpt-3.5-turbo

    references to combative situations or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    deals
    -0.82
    pod
    -0.75
    SAY
    -0.69
    hold
    -0.69
    mos
    -0.68
    cius
    -0.67
    profits
    -0.66
    medium
    -0.65
    minecraft
    -0.65
    demand
    -0.63
    POSITIVE LOGITS
     comb
    1.26
    inators
    1.02
    inational
    0.97
    inator
    0.85
    uations
    0.85
    inatory
    0.82
    ihar
    0.79
    itud
    0.79
    ative
    0.78
    atform
    0.77
    Activations Density 0.006%

    No Known Activations