Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 19139
    Prev
    Next
    INDEX
    Explanations

    instances of the word "rap"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of rap music

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fman
    -0.91
    ertodd
    -0.79
     Lauder
    -0.75
    ++++++++++++++++
    -0.75
     Samar
    -0.74
     Elves
    -0.70
    Split
    -0.69
     MSI
    -0.69
    Govern
    -0.67
     Templar
    -0.67
    POSITIVE LOGITS
     rap
    1.06
    acious
    1.04
    itone
    0.92
    acity
    0.90
    ican
    0.83
    hett
    0.82
    iqu
    0.81
    acus
    0.79
    iton
    0.79
    isphere
    0.79
    Activations Density 0.006%

    No Known Activations