© 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 EvalsExportsAPI 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. 2-RES-JB
    11. 7228
    Prev
    Next
    INDEX
    Explanations

    terms related to the fictional character 'Punisher'

    oai_token-act-pair · gpt-3.5-turbo

    references to "The Punisher" comic book character or related media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ORGE
    -0.77
    afety
    -0.70
    OTAL
    -0.70
    MO
    -0.69
    gow
    -0.68
    ALTH
    -0.67
     Mayer
    -0.67
    RAFT
    -0.67
    éļ
    -0.66
    è£ħ
    -0.65
    POSITIVE LOGITS
    pun
    1.06
    cheon
    1.05
    isher
    1.00
    ishment
    0.90
    ishable
    0.85
    nel
    0.84
     Pun
    0.81
    secut
    0.81
    ting
    0.80
    nels
    0.78
    Activations Density 0.006%

    No Known Activations