© 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. 8-RES-JB
    11. 6116
    Prev
    Next
    INDEX
    Explanations

    mentions of things being imitated or imitating something else

    oai_token-act-pair · gpt-3.5-turbo

    words related to being "immoral" or "immorality."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OPLE
    -0.68
     Morales
    -0.67
    escription
    -0.67
    Downloadha
    -0.66
     Sack
    -0.66
     Rav
    -0.65
    NetMessage
    -0.65
    ttes
    -0.63
     Wales
    -0.62
    ij士
    -0.61
    POSITIVE LOGITS
    itating
    1.15
    balanced
    1.14
    mer
    1.12
    manent
    1.08
    itates
    1.08
    itations
    1.06
    itated
    1.05
    mers
    1.00
    bal
    0.98
    bec
    0.93
    Activations Density 0.021%

    No Known Activations