© 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. 2810
    Prev
    Next
    INDEX
    Explanations

    the first person or entity to achieve a specific accomplishment

    oai_token-act-pair · gpt-3.5-turbo

    instances of individuals or roles achieving noteworthy accomplishments or firsts in various fields

    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
    utterstock
    -0.63
    deals
    -0.61
    ा
    -0.61
    asty
    -0.60
    izoph
    -0.60
    ãĤ¦ãĤ¹
    -0.60
     Secrets
    -0.59
    çī
    -0.59
    ruciating
    -0.57
    à©
    -0.57
    POSITIVE LOGITS
     ever
    1.08
     EVER
    0.96
     to
    0.93
    ever
    0.88
     diagnosed
    0.82
     officially
    0.80
     confirmed
    0.80
     approved
    0.80
     born
    0.79
     besides
    0.77
    Activations Density 0.143%

    No Known Activations