© 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. 8-RES-JB
    11. 4576
    Prev
    Next
    INDEX
    Explanations

    words related to electronic devices and technology

    oai_token-act-pair · gpt-3.5-turbo

    references to specific entities, titles, or notable organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     millenn
    -0.72
     Lanka
    -0.72
     horizont
    -0.63
    ivably
    -0.59
    hap
    -0.58
    Ñı
    -0.58
     è£ıè
    -0.57
    Tokens
    -0.56
     NASL
    -0.56
    ulative
    -0.56
    POSITIVE LOGITS
    "]=>
    0.75
     \'
    0.72
     deserves
    0.72
     receives
    0.71
     deems
    0.70
     existed
    0.69
    Reviewer
    0.67
    ="#
    0.66
     attends
    0.66
     wise
    0.65
    Activations Density 0.782%

    No Known Activations