© 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. 2-RES-JB
    11. 9028
    Prev
    Next
    INDEX
    Explanations

    numeric sequences

    oai_token-act-pair · gpt-3.5-turbo

    quantitative data related to numbers and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sph
    -0.53
    pn
    -0.50
    CHAT
    -0.50
    Feed
    -0.49
    RAW
    -0.48
    Media
    -0.48
     Conserv
    -0.48
    Struct
    -0.47
     lax
    -0.47
     fal
    -0.47
    POSITIVE LOGITS
     increments
    0.68
     apiece
    0.66
     installments
    0.63
     acres
    0.63
    pees
    0.62
     hrs
    0.61
    iversary
    0.60
     respectively
    0.60
     onwards
    0.60
    renheit
    0.57
    Activations Density 3.165%

    No Known Activations