Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 10133
    Prev
    Next
    INDEX
    Explanations

    words related to acts of defense or resistance

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to self-defense or coping mechanisms

    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
    videos
    -0.68
    asper
    -0.67
    ee
    -0.64
    users
    -0.63
     Grave
    -0.63
    agents
    -0.62
    operated
    -0.61
    eeks
    -0.61
    activated
    -0.60
    umo
    -0.59
    POSITIVE LOGITS
    ãĤ©
    1.03
    atown
    0.88
    cheon
    0.87
    jit
    0.85
    enance
    0.83
    ancial
    0.82
    rodu
    0.81
     fend
    0.78
    ously
    0.78
    rf
    0.75
    Activations Density 0.017%

    No Known Activations