© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    11. 1572
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names or individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals or entities associated with a particular surname

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BIP
    -0.81
    Impl
    -0.75
    MS
    -0.72
    Topics
    -0.71
    conscious
    -0.70
    GROUP
    -0.69
    Writing
    -0.67
    Ky
    -0.66
    udeb
    -0.66
    TE
    -0.65
    POSITIVE LOGITS
     Fah
    2.70
     KH
    0.90
     Cay
    0.75
     Clo
    0.73
     Nay
    0.71
     exch
    0.71
     Nex
    0.69
     Schiff
    0.68
     Sov
    0.66
     prest
    0.66
    Activations Density 0.012%

    No Known Activations