© 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. 1750
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "be it" and followed by a variety of scenarios or options

    oai_token-act-pair · gpt-3.5-turbo

    statements or phrases emphasizing hypothetical scenarios and conditions

    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
    SPONSORED
    -0.84
    ibilities
    -0.79
    ilib
    -0.74
    ATES
    -0.67
    encies
    -0.64
    idates
    -0.64
    ADVERTISEMENT
    -0.64
    resa
    -0.62
    iaries
    -0.61
    ynes
    -0.60
    POSITIVE LOGITS
     ours
    0.65
    audi
    0.63
     through
    0.61
     intentional
    0.60
     contemplating
    0.60
    LOD
    0.59
     physically
    0.59
     twe
    0.59
     photograp
    0.58
     suspending
    0.57
    Activations Density 0.204%

    No Known Activations