© 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. 8-RES-JB
    11. 9066
    Prev
    Next
    INDEX
    Explanations

    how something is done or perceived

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing alternative perspectives or reconsideration of existing views

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ynski
    -0.83
    ongo
    -0.78
     livest
    -0.74
    iry
    -0.69
    oute
    -0.69
     sugg
    -0.68
    unts
    -0.68
    usters
    -0.67
    erville
    -0.66
    uster
    -0.66
    POSITIVE LOGITS
     Sabha
    0.78
    fare
    0.73
     forever
    0.71
    ï
    0.70
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.70
    forward
    0.70
    footed
    0.70
    ward
    0.66
     Alma
    0.65
    finding
    0.63
    Activations Density 0.030%

    No Known Activations