© 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. 8-RES-JB
    11. 3095
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Swift" with varying levels of importance assigned to different contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the artist Taylor Swift

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    berra
    -0.79
    abases
    -0.77
    sembly
    -0.72
    terior
    -0.71
    abama
    -0.71
    chell
    -0.69
     ABE
    -0.66
    ++++
    -0.65
    gdala
    -0.65
    pse
    -0.65
    POSITIVE LOGITS
    heart
    0.84
    song
    0.81
    lings
    0.77
     Swim
    0.73
    Berry
    0.73
    Movie
    0.73
     Swift
    0.72
    Key
    0.71
    ies
    0.71
    lance
    0.71
    Activations Density 0.047%

    No Known Activations