© 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 EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 3007
    Prev
    Next
    INDEX
    Explanations

    statements indicating potential dangers or warnings

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    terms related to warnings and advisories regarding potential dangers or threats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phant
    -0.77
     ILCS
    -0.67
    cue
    -0.65
    elta
    -0.65
    FUN
    -0.63
    Interstitial
    -0.62
    artifacts
    -0.61
    anuts
    -0.60
    Answer
    -0.60
    itialized
    -0.59
    POSITIVE LOGITS
     against
    1.36
     omin
    0.99
    against
    0.93
     us
    0.89
     investors
    0.87
     listeners
    0.84
     Against
    0.83
     readers
    0.79
     about
    0.79
     citizens
    0.77
    Activations Density 0.086%

    No Known Activations