© 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. 9-RES-JB
    11. 3642
    Prev
    Next
    INDEX
    Explanations

    phrases related to social issues and statistics

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases indicating relationships or comparisons between elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utenberg
    -0.59
    hered
    -0.57
    ige
    -0.56
    gged
    -0.55
    ahime
    -0.54
    ighed
    -0.52
    ãĤ´ãĥ³
    -0.52
    BuyableInstoreAndOnline
    -0.51
    sed
    -0.51
    owered
    -0.51
    POSITIVE LOGITS
     consequently
    1.03
     therefore
    1.00
     furthermore
    0.98
     secondly
    0.98
     moreover
    0.93
     vice
    0.93
     hence
    0.91
     thus
    0.91
     thereby
    0.87
     thats
    0.76
    Activations Density 0.486%

    No Known Activations