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

    Neuronpedia

    Jacobian LensNEW
    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. 11-RES-JB
    11. 22037
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a general situation or condition

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating common occurrences or typical situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vernment
    -0.99
    ngth
    -0.77
    illion
    -0.75
    liv
    -0.73
    sheets
    -0.70
    jug
    -0.69
    anches
    -0.69
    mares
    -0.69
    ampions
    -0.69
    ulsion
    -0.68
    POSITIVE LOGITS
     case
    2.06
     Case
    1.35
    case
    1.30
     norm
    1.20
     cases
    1.15
    Case
    1.13
     CASE
    1.13
     fate
    1.10
     situation
    1.08
     outcome
    1.04
    Activations Density 0.093%

    No Known Activations