© 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. 9981
    Prev
    Next
    INDEX
    Explanations

    mentions of authors for scientific research papers

    oai_token-act-pair · gpt-3.5-turbo

    indicators of audience engagement or interest

    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
     cens
    -0.86
    etheless
    -0.85
     fleeing
    -0.83
     unseen
    -0.82
     stray
    -0.79
     suspected
    -0.79
     neglig
    -0.78
     reflex
    -0.77
     specialized
    -0.76
     displaced
    -0.76
    POSITIVE LOGITS
    AMY
    1.71
    Question
    1.64
    Anyway
    1.59
    Secondly
    1.58
    TON
    1.53
    Advertisement
    1.53
    You
    1.51
    Interview
    1.51
    Then
    1.50
    So
    1.50
    Activations Density 0.219%

    No Known Activations