© 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. 8-RES-JB
    11. 1315
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by specific anatomical or geographical terms

    oai_token-act-pair · gpt-3.5-turbo

    references to spatial positions above or below specific landmarks or levels

    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
    behind
    -0.83
    76561
    -0.78
    olkien
    -0.76
    PsyNetMessage
    -0.70
    CLA
    -0.68
    MRI
    -0.67
    CVE
    -0.67
    Between
    -0.67
    QL
    -0.66
    OY
    -0.64
    POSITIVE LOGITS
     horizon
    1.10
     fray
    0.94
     threshold
    0.94
     surface
    0.92
     fold
    0.86
     usual
    0.81
     waist
    0.79
     level
    0.78
     parap
    0.77
     crest
    0.77
    Activations Density 0.096%

    No Known Activations