© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8-RES-JB
    11. 14491
    Prev
    Next
    INDEX
    Explanations

    phrases related to searching for something or someone

    oai_token-act-pair · gpt-3.5-turbo

    references to personal agency and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Enlarge
    -0.62
    icka
    -0.61
     Pulitzer
    -0.61
     Philly
    -0.58
     Vers
    -0.56
     POLITICO
    -0.55
     Vu
    -0.54
    iversary
    -0.53
     Haf
    -0.52
     Mandal
    -0.52
    POSITIVE LOGITS
    etheless
    1.06
    )).
    0.86
    ''.
    0.85
    theless
    0.84
    '.
    0.78
     nevertheless
    0.77
    ]).
    0.77
    ?".
    0.77
     nonetheless
    0.75
    ]."
    0.75
    Activations Density 1.698%

    No Known Activations