© 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. 10-RES-JB
    11. 11609
    Prev
    Next
    INDEX
    Explanations

    information related to criminal incidents and investigations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the definite article "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hops
    -0.88
    warts
    -0.85
    TPP
    -0.76
    Boost
    -0.75
    Allows
    -0.75
    Europe
    -0.74
    ftime
    -0.73
    indust
    -0.73
    thood
    -0.72
    adh
    -0.72
    POSITIVE LOGITS
     assailant
    1.37
     incident
    1.36
     victim
    1.36
     attacker
    1.30
     unidentified
    1.26
     suspect
    1.25
     altercation
    1.24
     perpetrator
    1.20
     assailants
    1.19
     gunman
    1.18
    Activations Density 0.238%

    No Known Activations