© 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. 3435
    Prev
    Next
    INDEX
    Explanations

    information related to sports drafts and player selections

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

    details about player drafts, achievements, and statistics in hockey

    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
    >[
    -0.77
    morning
    -0.75
    #$
    -0.71
     Godd
    -0.66
    Enlarge
    -0.65
    OIL
    -0.64
    URI
    -0.63
    heit
    -0.63
     Collider
    -0.59
    ickr
    -0.58
    POSITIVE LOGITS
     stint
    0.88
     colleg
    0.86
     totaling
    0.79
     collegiate
    0.77
     totaled
    0.77
     AHL
    0.76
     appearances
    0.75
     tally
    0.75
    incial
    0.73
     compiling
    0.71
    Activations Density 0.296%

    No Known Activations