© 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. 3-RES-JB
    11. 10796
    Prev
    Next
    INDEX
    Explanations

    mentions of being imprisoned or serving time behind bars

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "bars," relating to confinement or places where people gather

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ctive
    -0.91
    lihood
    -0.75
    IBLE
    -0.74
    sie
    -0.73
    EngineDebug
    -0.71
    UAL
    -0.70
    ALLY
    -0.69
    åĬ
    -0.68
    ULAR
    -0.67
     GENERAL
    -0.66
    POSITIVE LOGITS
    hops
    1.07
     bars
    1.04
    poon
    1.03
    hop
    1.02
    manship
    0.97
    becue
    0.95
    itone
    0.90
    mith
    0.89
    bell
    0.86
    bars
    0.86
    Activations Density 0.005%

    No Known Activations