© 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. 20313
    Prev
    Next
    INDEX
    Explanations

    locations or places associated with ports

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations and ports

    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
    schild
    -0.78
    sect
    -0.66
     Witnesses
    -0.61
    kai
    -0.60
     Fold
    -0.59
    organic
    -0.59
    sbm
    -0.58
    Witness
    -0.58
    ãĥķãĤ©
    -0.58
     categories
    -0.55
    POSITIVE LOGITS
    uese
    1.03
    sylvania
    0.81
    ão
    0.76
    iture
    0.76
    atche
    0.72
    cially
    0.72
    lished
    0.68
    BILITIES
    0.67
    asus
    0.67
    uez
    0.67
    Activations Density 0.166%

    No Known Activations