© 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. 4-RES-JB
    11. 23997
    Prev
    Next
    INDEX
    Explanations

    words related to a specific fictional character named "Falcon."

    oai_token-act-pair · gpt-3.5-turbo

    the word "Falcon" and its variations in various contexts

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

    No Comments

    Negative Logits
    ortium
    -0.71
     nursery
    -0.69
     Tune
    -0.66
    ynthesis
    -0.66
    sburgh
    -0.65
    LESS
    -0.65
     Tycoon
    -0.64
     tune
    -0.63
     compounded
    -0.62
     Regulatory
    -0.62
    POSITIVE LOGITS
    stad
    1.02
     Fal
    0.97
    vey
    0.90
    cohol
    0.89
    Fal
    0.87
    itz
    0.84
    quet
    0.83
    thouse
    0.83
    unte
    0.81
    renheit
    0.81
    Activations Density 0.007%

    No Known Activations