© 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. 10-RES-JB
    11. 2749
    Prev
    Next
    INDEX
    Explanations

    references to various types of media players or technologies

    oai_token-act-pair · gpt-3.5-turbo

    references to various models of portable media players

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stal
    -0.78
    idad
    -0.75
    Else
    -0.69
    ptive
    -0.69
    worldly
    -0.69
    istically
    -0.67
    nces
    -0.67
    mberg
    -0.66
     confinement
    -0.62
    sword
    -0.61
    POSITIVE LOGITS
    AA
    1.09
    PLIC
    1.01
    EG
    0.99
    LAB
    0.93
    TG
    0.91
    rodu
    0.91
    OA
    0.91
    412
    0.89
    FS
    0.87
    Ps
    0.85
    Activations Density 0.023%

    No Known Activations