© 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. 22607
    Prev
    Next
    INDEX
    Explanations

    instances where actions are described

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to guidelines and requirements

    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
    veland
    -0.63
    âĸ¬
    -0.60
    onest
    -0.55
     allegiance
    -0.54
    orthy
    -0.52
     Franch
    -0.52
    idency
    -0.51
    antine
    -0.51
    chance
    -0.51
     Canad
    -0.51
    POSITIVE LOGITS
     above
    2.08
     below
    1.83
     mentioned
    1.76
    above
    1.71
     listed
    1.67
     outlined
    1.61
     described
    1.56
     discussed
    1.54
    below
    1.49
     foregoing
    1.43
    Activations Density 0.474%

    No Known Activations