© 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. 9845
    Prev
    Next
    INDEX
    Explanations

    conversations or dialogues involving asking and responding

    oai_token-act-pair · gpt-3.5-turbo

    expressions of dialogue and emotional states

    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
     Philly
    -0.86
     Amtrak
    -0.83
    espie
    -0.79
     Ukip
    -0.79
     Dublin
    -0.77
    BILL
    -0.77
     Rudd
    -0.75
     Dixon
    -0.75
    Baltimore
    -0.74
     Bridgewater
    -0.73
    POSITIVE LOGITS
    ãĢİ
    1.71
     ãĢĮ
    1.65
    ãĢIJ
    1.55
     Takeru
    1.40
    ãĢĮ
    1.32
    ãĢ
    1.29
     Makoto
    1.28
     Sakuya
    1.26
     å¤
    1.24
    sama
    1.24
    Activations Density 0.684%

    No Known Activations