© 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. 1-RES-JB
    11. 16358
    Prev
    Next
    INDEX
    Explanations

    references to investigations or examinations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "scrutiny."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thus
    -0.80
    activated
    -0.77
    tre
    -0.77
    tein
    -0.72
    activate
    -0.68
    gran
    -0.67
    sell
    -0.64
    ird
    -0.63
    joining
    -0.63
    stead
    -0.63
    POSITIVE LOGITS
     scrutiny
    1.48
     scrutin
    0.88
    é¾įå¥ij士
    0.82
     levied
    0.77
    oreAnd
    0.76
     Probe
    0.76
    wcsstore
    0.76
     dilig
    0.75
     examinations
    0.75
    terness
    0.74
    Activations Density 0.006%

    No Known Activations