© 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. 18460
    Prev
    Next
    INDEX
    Explanations

    details related to legal cases or criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal conditions and restrictions

    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
    erenn
    -0.64
    ahime
    -0.63
     globally
    -0.63
    cients
    -0.63
    ankind
    -0.61
     fantastic
    -0.60
     nominate
    -0.60
     commemorate
    -0.60
     rejoice
    -0.59
     visionary
    -0.59
    POSITIVE LOGITS
     hers
    0.93
    VERTISEMENT
    0.75
     incrim
    0.74
     misdemeanor
    0.74
    igslist
    0.73
     paperwork
    0.72
     medication
    0.72
     foreclosure
    0.71
     subpoena
    0.69
     reimb
    0.67
    Activations Density 1.717%

    No Known Activations