© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 7762
    Prev
    Next
    INDEX
    Explanations

    mentions of quantity or predominance within a specific group or context

    oai_token-act-pair · gpt-3.5-turbo

    phrases that quantify opinions or consensus among a large group

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EStream
    -0.75
    gypt
    -0.69
    acus
    -0.69
    arium
    -0.68
    abl
    -0.67
    ĸļ
    -0.66
    usp
    -0.66
    resy
    -0.64
    uel
    -0.63
    ħĭ
    -0.63
    POSITIVE LOGITS
     respondents
    0.78
     occurrences
    0.71
     people
    0.70
     households
    0.70
     PEOPLE
    0.69
    ergic
    0.66
     Americans
    0.66
     those
    0.66
     blame
    0.66
     participants
    0.66
    Activations Density 0.082%

    No Known Activations