© 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. 17646
    Prev
    Next
    INDEX
    Explanations

    references to identification, like ID cards or numbers

    oai_token-act-pair · gpt-3.5-turbo

    various forms of identification and references to ID numbers

    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
    ategory
    -0.76
    theless
    -0.73
    cffff
    -0.72
     Silence
    -0.70
    iful
    -0.69
    orld
    -0.68
    ruciating
    -0.67
    bilt
    -0.67
    terday
    -0.66
     Sounds
    -0.66
    POSITIVE LOGITS
    iots
    1.04
    aho
    1.01
    entity
    0.96
    DEN
    0.91
    ictionary
    0.89
     badges
    0.88
     badge
    0.87
    EA
    0.87
    ENT
    0.86
     cards
    0.85
    Activations Density 0.029%

    No Known Activations