© 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. 1-RES-JB
    11. 3521
    Prev
    Next
    INDEX
    Explanations

    financial terms or phrases related to restructuring debts

    oai_token-act-pair · gpt-3.5-turbo

    indicators of statistical data or census information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ega
    -0.75
     Cald
    -0.70
     Afric
    -0.69
    adium
    -0.68
     Chaff
    -0.68
     Xin
    -0.67
     Chimera
    -0.67
     Defenders
    -0.67
    mere
    -0.65
     Whedon
    -0.65
    POSITIVE LOGITS
    ãĤ¯
    0.74
    IDENT
    0.68
    »Ĵ
    0.68
    BER
    0.66
    ynthesis
    0.66
    FORMATION
    0.65
    olkien
    0.64
    EGIN
    0.64
    ITED
    0.63
    UNCH
    0.62
    Activations Density 0.000%

    No Known Activations