© 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. 11-RES-JB
    11. 10065
    Prev
    Next
    INDEX
    Explanations

    statements indicating conflict or disagreement

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to agreement and acceptance in negotiations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     to
    -0.54
    ombo
    -0.51
     To
    -0.51
     TO
    -0.49
     attRot
    -0.47
    itsu
    -0.47
    iques
    -0.46
     nicknamed
    -0.45
    to
    -0.45
     handy
    -0.44
    POSITIVE LOGITS
    âĢ
    0.94
     âĢ
    0.85
     denotes
    0.83
     belongs
    0.81
    ?,
    0.79
     consists
    0.79
     coincides
    0.78
     rests
    0.77
     implies
    0.76
     derives
    0.76
    Activations Density 1.247%

    No Known Activations