© 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. 4-RES-JB
    11. 1986
    Prev
    Next
    INDEX
    Explanations

    names of specific individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character "Ļ"

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

    No Comments

    Negative Logits
     carbohyd
    -0.80
     fortun
    -0.74
     Seym
    -0.73
     mathemat
    -0.73
     succession
    -0.73
     inhib
    -0.70
     metic
    -0.68
     disadvant
    -0.65
     hemor
    -0.65
     tremend
    -0.64
    POSITIVE LOGITS
    DEN
    0.95
    ï¸ı
    0.89
    Ļ
    0.81
    ĩ
    0.79
    kay
    0.79
    DL
    0.78
    audi
    0.76
    é¾įåĸļ士
    0.76
    strom
    0.74
    İ
    0.74
    Activations Density 0.157%

    No Known Activations