© 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. 9-RES-JB
    11. 14334
    Prev
    Next
    INDEX
    Explanations

    book, movie, and TV series titles

    oai_token-act-pair · gpt-3.5-turbo

    references to specific fictional universes or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jri
    -0.89
    ntil
    -0.73
    asse
    -0.71
    reply
    -0.71
    STATE
    -0.71
    scl
    -0.70
    cipled
    -0.69
    itness
    -0.68
    hap
    -0.68
    olicited
    -0.67
    POSITIVE LOGITS
     trilogy
    1.40
     Trilogy
    1.31
     Characters
    1.22
     sequels
    1.12
     Animated
    1.10
     mythology
    1.10
     novels
    1.08
     films
    1.03
     movies
    1.02
     canon
    1.01
    Activations Density 0.361%

    No Known Activations