© 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. 4176
    Prev
    Next
    INDEX
    Explanations

    information related to competitive tournaments and matches

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

    components related to tournament structure and rules

    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
    gur
    -0.87
    dylib
    -0.86
    uti
    -0.86
    irrel
    -0.82
    framework
    -0.71
    icz
    -0.69
    soType
    -0.68
    irit
    -0.67
    alore
    -0.67
    ĸļ
    -0.65
    POSITIVE LOGITS
     Playoffs
    1.22
     seeded
    1.21
     Rounds
    1.16
     Finals
    1.13
     loser
    1.11
     playoffs
    1.09
     semifinals
    1.08
     Playoff
    1.05
     elimination
    1.05
     Elim
    1.01
    Activations Density 0.243%

    No Known Activations