© 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. 6-RES-JB
    11. 9296
    Prev
    Next
    INDEX
    Explanations

    keywords related to Batman

    oai_token-act-pair · gpt-3.5-turbo

    references to Batman and related characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mble
    -1.12
    ateur
    -0.81
    sweet
    -0.79
    xual
    -0.76
    rition
    -0.75
    ntil
    -0.75
    OPLE
    -0.75
    olulu
    -0.74
    pec
    -0.73
    ormons
    -0.72
    POSITIVE LOGITS
     Begins
    1.17
     Arkham
    1.00
     villains
    0.85
    Batman
    0.84
     Returns
    0.81
     villain
    0.79
     Batman
    0.78
     Bros
    0.77
     Anth
    0.72
     Comics
    0.71
    Activations Density 0.025%

    No Known Activations