© 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. 1-RES-JB
    11. 3537
    Prev
    Next
    INDEX
    Explanations

    references to investigations

    oai_token-act-pair · gpt-3.5-turbo

    references to investigations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dos
    -0.71
    coded
    -0.70
    absolute
    -0.66
     mindless
    -0.64
    shared
    -0.64
    birth
    -0.64
    piring
    -0.63
    generic
    -0.62
    perm
    -0.61
    noxious
    -0.61
    POSITIVE LOGITS
     investigation
    1.26
     investigations
    1.08
     inquiry
    1.03
     Investigation
    1.01
     Inquiry
    0.97
     probe
    0.97
     investigating
    0.95
     investigates
    0.94
     probes
    0.93
     probing
    0.92
    Activations Density 0.024%

    No Known Activations