© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 12545
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific perspective or viewpoint

    oai_token-act-pair · gpt-3.5-turbo

    articles and determiners indicating quantity or specificity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    facts
    -0.73
    blems
    -0.72
    perty
    -0.71
    ases
    -0.66
    heses
    -0.66
    hes
    -0.65
    advertisement
    -0.63
    cas
    -0.62
    Frameworks
    -0.62
    Adapt
    -0.62
    POSITIVE LOGITS
     standpoint
    1.52
     vantage
    1.23
     perspective
    1.09
     outset
    1.08
     viewpoint
    0.92
     afar
    0.91
     distance
    0.87
     onwards
    0.84
    ratch
    0.82
     infancy
    0.82
    Activations Density 0.160%

    No Known Activations