© 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. 11-RES-JB
    11. 4072
    Prev
    Next
    INDEX
    Explanations

    instances of words related to making alterations or modifications

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "change" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    glas
    -0.80
    eous
    -0.70
    enium
    -0.69
    tic
    -0.69
    inth
    -0.65
    vered
    -0.65
    ictionary
    -0.65
    amina
    -0.63
    sie
    -0.62
    kamp
    -0.62
    POSITIVE LOGITS
     gears
    1.23
     directions
    1.20
     tack
    1.19
     diapers
    1.13
     direction
    1.08
     course
    1.04
     minds
    0.96
     sides
    0.95
     allegiance
    0.94
     formats
    0.93
    Activations Density 0.067%

    No Known Activations