© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 600
    Prev
    Next
    INDEX
    Explanations

    descriptions of animated movie characters

    oai_token-act-pair · gpt-3.5-turbo

    references to characters and story elements in the film "Frozen."

    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
    ichick
    -1.04
     Karachi
    -1.03
    ombat
    -0.98
     Chomsky
    -0.98
    Pakistan
    -0.96
    uterte
    -0.94
    Pak
    -0.88
    vernment
    -0.85
     Bombay
    -0.84
     Vietnam
    -0.83
    POSITIVE LOGITS
     Elsa
    2.54
    Elsa
    2.27
     Anna
    2.22
    Anna
    2.02
     Frozen
    1.75
     Krist
    1.56
     Sven
    1.43
    rozen
    1.42
     Ol
    1.39
    Krist
    1.37
    Activations Density 0.109%

    No Known Activations