© 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. 4-RES-JB
    11. 11243
    Prev
    Next
    INDEX
    Explanations

    symbols and characters that likely represent a specific language or encoding format

    oai_token-act-pair · gpt-3.5-turbo

    special characters and symbols, likely indicating non-standard text or formatting errors

    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
    istics
    -0.77
    auder
    -0.73
    ormal
    -0.72
    ials
    -0.71
    irrel
    -0.69
    ilater
    -0.68
    ority
    -0.68
    ufact
    -0.67
    antha
    -0.66
     elim
    -0.66
    POSITIVE LOGITS
    ·
    1.15
    çİĭ
    1.07
    ¸
    1.07
    °
    1.04
    ı
    1.03
    ¾
    1.02
    ½
    0.97
    ¶
    0.93
    ®
    0.93
    Ĺ
    0.91
    Activations Density 0.008%

    No Known Activations