© 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. 4-RES-JB
    11. 14663
    Prev
    Next
    INDEX
    Explanations

    references to items that are available for use or consumption

    oai_token-act-pair · gpt-3.5-turbo

    terms related to playability and usability in games and systems

    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
    olog
    -0.85
    romy
    -0.82
    udic
    -0.80
    hon
    -0.80
    thodox
    -0.77
    arius
    -0.75
    omen
    -0.74
    oly
    -0.73
    str
    -0.73
    ogram
    -0.72
    POSITIVE LOGITS
     playable
    1.05
    lihood
    0.92
    halla
    0.88
     usable
    0.88
    ãĥ´
    0.80
    GoldMagikarp
    0.78
    ãĤ¤ãĥĪ
    0.76
    æĹ
    0.74
    atable
    0.71
    CLASSIFIED
    0.70
    Activations Density 0.021%

    No Known Activations