© 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. 12283
    Prev
    Next
    INDEX
    Explanations

    organizations and institutions related to policy and research

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to policy reports and evaluations

    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
     captcha
    -0.86
     customs
    -0.73
     racists
    -0.72
     cheaply
    -0.71
     rites
    -0.70
     constit
    -0.67
     bans
    -0.66
     closing
    -0.66
     colours
    -0.65
     cruelty
    -0.65
    POSITIVE LOGITS
     Analysis
    1.14
     Institute
    1.02
     Analyst
    0.99
     Clinic
    0.95
     Studies
    0.95
    odox
    0.92
     Analytics
    0.91
     Research
    0.89
    Brook
    0.89
     Blog
    0.88
    Activations Density 0.094%

    No Known Activations