© 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. 0-RES-JB
    11. 2312
    Prev
    Next
    INDEX
    Explanations

    words related to illegal activities or violations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to drug usage and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Shroud
    -0.65
     neutron
    -0.59
    likely
    -0.58
     Ant
    -0.58
     dist
    -0.57
    rising
    -0.57
     latitude
    -0.56
     totality
    -0.56
     undert
    -0.55
    ext
    -0.55
    POSITIVE LOGITS
    gging
    3.60
    gged
    3.57
    ggy
    3.10
    ggie
    2.93
    gger
    2.29
    ggies
    2.24
    gg
    2.00
    ggle
    1.95
    ggles
    1.52
    gs
    1.42
    Activations Density 0.020%

    No Known Activations