© 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. 1-RES-JB
    11. 3404
    Prev
    Next
    INDEX
    Explanations

    verbs related to fighting or struggling

    oai_token-act-pair · gpt-3.5-turbo

    references to combat or struggle

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /-
    -0.72
    ordinate
    -0.66
    ixel
    -0.65
    entric
    -0.63
    effect
    -0.60
    Newsletter
    -0.59
    ffic
    -0.59
    ateral
    -0.59
    mr
    -0.59
    orph
    -0.58
    POSITIVE LOGITS
     fought
    1.26
     waged
    0.93
     against
    0.93
    fight
    0.92
     fights
    0.90
    fights
    0.89
     valiant
    0.83
     battles
    0.80
     spar
    0.77
    escription
    0.77
    Activations Density 0.007%

    No Known Activations