© 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. 0-RES-JB
    11. 604
    Prev
    Next
    INDEX
    Explanations

    legal and formal terms, especially those related to classification and designation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to official designations and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arty
    -0.68
    plugins
    -0.66
    live
    -0.63
     confronted
    -0.63
     listened
    -0.62
     helpless
    -0.60
     ur
    -0.59
     uncontroll
    -0.59
     Terr
    -0.58
     fuelled
    -0.58
    POSITIVE LOGITS
     designation
    3.81
     moniker
    2.09
     classification
    2.07
     Classification
    1.68
     certification
    1.64
     distinction
    1.59
     descriptor
    1.55
     designate
    1.46
     nickname
    1.45
     appell
    1.39
    Activations Density 0.018%

    No Known Activations