© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 1711
    Prev
    Next
    INDEX
    Explanations

    entities or concepts often associated with power dynamics and influence

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to entrapment or entanglement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Responsibility
    -0.74
    Games
    -0.68
    Universal
    -0.65
    pmwiki
    -0.63
    TPPStreamerBot
    -0.63
    Ô
    -0.62
    ãĥ£
    -0.62
     Goth
    -0.61
    Beer
    -0.60
    Jump
    -0.59
    POSITIVE LOGITS
    ourage
    1.03
    ailed
    1.02
    ailing
    0.92
    rench
    0.92
    renched
    0.91
    uring
    0.91
    iring
    0.90
    inence
    0.90
    repre
    0.88
    rained
    0.88
    Activations Density 0.018%

    No Known Activations