© 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. 11958
    Prev
    Next
    INDEX
    Explanations

    words related to crime, corruption, and dishonesty

    oai_token-act-pair · gpt-3.5-turbo

    words related to crime and related social issues

    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
    bh
    -0.60
    ©¶æ¥µ
    -0.59
    ERO
    -0.59
    amiya
    -0.57
    Downloadha
    -0.57
    mb
    -0.56
    ahime
    -0.56
    zek
    -0.56
    mini
    -0.55
    atform
    -0.54
    POSITIVE LOGITS
    erers
    0.66
     Hunters
    0.64
    istani
    0.63
     subclass
    0.61
     Tycoon
    0.60
    ographer
    0.60
    lords
    0.59
     lover
    0.59
     ident
    0.58
     Lobby
    0.58
    Activations Density 0.343%

    No Known Activations