© 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. 6696
    Prev
    Next
    INDEX
    Explanations

    disclaimers and notes about content reliability

    oai_token-act-pair · gpt-3.5-turbo

    disclaimers and statements about the nature of content and opinions

    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
    iddler
    -0.70
    cling
    -0.65
    »Ĵ
    -0.64
    dor
    -0.62
    SPONSORED
    -0.61
     Chal
    -0.59
    trap
    -0.59
    vati
    -0.59
    luaj
    -0.58
    Secretary
    -0.58
    POSITIVE LOGITS
     copyrighted
    1.02
     assumes
    0.98
     tentative
    0.98
     approximate
    0.96
     unofficial
    0.94
     Actual
    0.93
     subjective
    0.93
     provisional
    0.91
     NOT
    0.90
    claimer
    0.88
    Activations Density 0.395%

    No Known Activations