© 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. 0-RES-JB
    11. 420
    Prev
    Next
    INDEX
    Explanations

    words related to legal actions and conflicts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to investigative roles or actions

    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
     Prem
    -0.68
     Nep
    -0.63
     raids
    -0.61
     disp
    -0.60
     sector
    -0.59
     tune
    -0.59
     posting
    -0.59
     Rom
    -0.58
     central
    -0.58
     Tel
    -0.58
    POSITIVE LOGITS
    igator
    4.60
    igators
    3.94
    igation
    1.86
    igating
    1.68
    igate
    1.48
    igated
    1.35
    iator
    1.05
    igers
    1.03
    osaurus
    1.01
    angler
    0.98
    Activations Density 0.006%

    No Known Activations