© 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. 3-RES-JB
    11. 15182
    Prev
    Next
    INDEX
    Explanations

    abbreviations related to legal proceedings or documents

    oai_token-act-pair · gpt-3.5-turbo

    references to the Public Interest Litigation (PIL) process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uyomi
    -0.79
    rano
    -0.76
    perature
    -0.76
    ©¶æ
    -0.74
    oÄŁ
    -0.74
    hra
    -0.71
    lies
    -0.71
     Crunch
    -0.70
    hend
    -0.68
    ende
    -0.68
    POSITIVE LOGITS
    ibrary
    1.17
    UTION
    1.15
    IL
    1.07
    IENT
    1.03
    DER
    1.03
    LET
    1.02
    ER
    0.98
    IAS
    0.98
    MET
    0.97
    ADA
    0.96
    Activations Density 0.006%

    No Known Activations