© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 20271
    Prev
    Next
    INDEX
    Explanations

    commands, directives or urgent instructions

    oai_token-act-pair · gpt-3.5-turbo

    commands or urgent requests for action

    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
    weet
    -0.81
    LGBT
    -0.74
    olkien
    -0.74
    uably
    -0.73
     millennial
    -0.73
     embraced
    -0.73
    ibia
    -0.73
    onut
    -0.72
    iqueness
    -0.70
     stereotyp
    -0.70
    POSITIVE LOGITS
     reinforcements
    1.25
     Militia
    1.20
     evacuate
    1.08
     evac
    1.07
     patrol
    1.06
     Lieutenant
    1.04
     patrols
    1.03
     Ops
    1.03
     supplies
    1.03
     convoy
    1.02
    Activations Density 0.792%

    No Known Activations