© 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. 11253
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal proceedings

    oai_token-act-pair · gpt-3.5-turbo

    themes related to conflict and injustice

    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
    enne
    -0.62
    Cooldown
    -0.59
    details
    -0.55
    lopp
    -0.55
    olen
    -0.55
    DX
    -0.54
    ophon
    -0.54
    Focus
    -0.53
    detail
    -0.53
    enge
    -0.52
    POSITIVE LOGITS
     guiActiveUnfocused
    0.71
     sue
    0.69
     onto
    0.67
     join
    0.66
     testify
    0.65
     submit
    0.65
     scrambling
    0.63
     accountable
    0.62
     collaborate
    0.62
     participate
    0.62
    Activations Density 0.725%

    No Known Activations