© 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. 1-RES-JB
    11. 20028
    Prev
    Next
    INDEX
    Explanations

    commands related to software updates or installations

    oai_token-act-pair · gpt-3.5-turbo

    commands or instructions related to package management in software

    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
     Archdemon
    -0.74
     conson
    -0.63
     Lich
    -0.62
     lik
    -0.62
     prophes
    -0.62
     retirement
    -0.61
     flavours
    -0.61
    worldly
    -0.61
     caution
    -0.60
     governing
    -0.60
    POSITIVE LOGITS
    TING
    1.14
    get
    1.04
    gets
    1.02
    tin
    0.93
    ters
    0.92
    fix
    0.88
    away
    0.88
    ãĥ¼ãĥĨãĤ£
    0.81
    ãĥİ
    0.81
    href
    0.80
    Activations Density 0.016%

    No Known Activations