© 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. 20318
    Prev
    Next
    INDEX
    Explanations

    interactions or confrontations between individuals

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating confrontation or conflict

    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
    Wars
    -0.77
     administ
    -0.64
    responsible
    -0.64
     Workers
    -0.64
     bom
    -0.63
    Ĥª
    -0.62
     Tomato
    -0.61
     Orders
    -0.61
     batches
    -0.61
    roups
    -0.61
    POSITIVE LOGITS
     face
    1.22
     Face
    1.19
    face
    1.14
     FACE
    1.10
    Face
    1.07
    surface
    0.86
     faces
    0.81
    sid
    0.81
    Depth
    0.80
     facial
    0.80
    Activations Density 0.028%

    No Known Activations