© 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. 4-RES-JB
    11. 24100
    Prev
    Next
    INDEX
    Explanations

    terms related to deliverables or items being provided or offered

    oai_token-act-pair · gpt-3.5-turbo

    words related to items or concepts that are capable of being delivered or arranged

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

    No Comments

    Negative Logits
    eson
    -0.77
    aeper
    -0.76
    elin
    -0.74
    otaur
    -0.73
     Kern
    -0.69
    orney
    -0.68
    iversary
    -0.67
     Shank
    -0.66
    gerald
    -0.65
    lar
    -0.63
    POSITIVE LOGITS
    poons
    1.14
    poon
    0.85
    cffffcc
    0.80
    MpServer
    0.79
    NetMessage
    0.74
    pedia
    0.70
    rights
    0.69
    omething
    0.69
    ensical
    0.68
    cript
    0.67
    Activations Density 0.019%

    No Known Activations