© 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. 1349
    Prev
    Next
    INDEX
    Explanations

    time-related events or actions indicated by the occurrences of 'once' or 'twice'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the number two and phrases indicating duality or a comparison between two entities

    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
     Pastebin
    -0.72
    paralle
    -0.68
    +.
    -0.66
    vr
    -0.65
    rawdownloadcloneembedreportprint
    -0.65
    much
    -0.62
    kay
    -0.61
    ......
    -0.60
    overs
    -0.60
    .]
    -0.60
    POSITIVE LOGITS
     foreground
    0.67
     sexes
    0.65
     statically
    0.65
    itative
    0.60
     fists
    0.60
     literal
    0.60
     neutral
    0.58
     outright
    0.56
     benevolent
    0.55
     mundane
    0.55
    Activations Density 0.302%

    No Known Activations