© 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. 17778
    Prev
    Next
    INDEX
    Explanations

    references to an organization or term involving "CB" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to Canadian Border Services and related 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
    wine
    -0.71
    lihood
    -0.70
    arily
    -0.64
    zzo
    -0.64
    igators
    -0.63
    atics
    -0.62
     xen
    -0.62
    aciously
    -0.62
    umerable
    -0.61
    orio
    -0.60
    POSITIVE LOGITS
    anut
    0.81
    dar
    0.80
    ahn
    0.78
    oard
    0.77
    GB
    0.76
    SEA
    0.76
    DT
    0.74
    QB
    0.74
    PP
    0.74
    rief
    0.73
    Activations Density 0.032%

    No Known Activations