© 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. 10-RES-JB
    11. 21424
    Prev
    Next
    INDEX
    Explanations

    occurrences of words related to analysis, observation, and evaluation

    oai_token-act-pair · gpt-3.5-turbo

    references to evidence and observations supporting claims or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    danger
    -0.65
    "!
    -0.65
    cott
    -0.64
    ajor
    -0.60
    ookie
    -0.60
    ordable
    -0.58
    requisite
    -0.58
     Pradesh
    -0.57
    owe
    -0.57
    apo
    -0.57
    POSITIVE LOGITS
     lately
    1.12
     anecd
    0.91
     graphs
    0.82
     nowadays
    0.78
     histories
    0.77
     objectively
    0.76
     catalogue
    0.73
     testimonies
    0.71
     firsthand
    0.70
     archives
    0.69
    Activations Density 0.385%

    No Known Activations