© 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. 14144
    Prev
    Next
    INDEX
    Explanations

    people or organizations speaking on behalf of others

    oai_token-act-pair · gpt-3.5-turbo

    references to spokespersons and their statements

    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
    Exper
    -0.72
    venge
    -0.70
     pioneers
    -0.69
     ballot
    -0.69
     Beaut
    -0.67
     murderer
    -0.66
    rafted
    -0.64
     scores
    -0.64
     deserving
    -0.63
     killers
    -0.63
    POSITIVE LOGITS
     declined
    1.36
     emailed
    1.04
     clarified
    1.04
     spokeswoman
    1.00
     reiterated
    0.97
     spokesman
    0.94
     replied
    0.91
     told
    0.90
    ©¶æ¥µ
    0.90
     emphasized
    0.89
    Activations Density 0.292%

    No Known Activations