© 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. 800
    Prev
    Next
    INDEX
    Explanations

    mentions of different languages and unique characters

    oai_token-act-pair · gpt-3.5-turbo

    segments of text characterized by complex or abstract elements, potentially in a literary or artistic context

    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
    Hamilton
    -0.87
    Houston
    -0.77
    Harris
    -0.77
    Australian
    -0.76
     Revelations
    -0.72
    Texas
    -0.70
    CLASSIFIED
    -0.70
    Alice
    -0.70
    Warren
    -0.70
     Ellison
    -0.69
    POSITIVE LOGITS
    Äĩ
    1.75
    Äį
    1.71
    Ä
    1.53
    Å¡
    1.51
     Sloven
    1.44
     Ä
    1.41
    Å
    1.37
     Å
    1.32
    ovi
    1.26
    È
    1.25
    Activations Density 0.130%

    No Known Activations