© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 6642
    Prev
    Next
    INDEX
    Explanations

    mentions of the death penalty

    oai_token-act-pair · gpt-3.5-turbo

    references to the death penalty

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

    No Comments

    Negative Logits
    arity
    -0.91
    BN
    -0.89
    KY
    -0.87
    soType
    -0.82
     Jord
    -0.80
    INC
    -0.80
    ivas
    -0.79
    Ni
    -0.79
    CRE
    -0.77
    é¾įåĸļ士
    -0.75
    POSITIVE LOGITS
     incarcer
    1.08
     inmate
    1.00
     forfeiture
    0.92
     penalty
    0.91
     starvation
    0.89
     incarcerated
    0.87
     torture
    0.87
     abolition
    0.86
     inmates
    0.85
     convict
    0.84
    Activations Density 0.033%

    No Known Activations