© 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. 2-RES-JB
    11. 3899
    Prev
    Next
    INDEX
    Explanations

    references to the genre of music named "rap"

    oai_token-act-pair · gpt-3.5-turbo

    terms and references associated with rap music

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fman
    -0.84
    ++++++++++++++++
    -0.78
     Lauder
    -0.78
    Split
    -0.70
     Samar
    -0.68
     Elves
    -0.66
     Templar
    -0.66
    ########
    -0.66
     Columb
    -0.65
    ertodd
    -0.64
    POSITIVE LOGITS
     rap
    1.05
    acious
    0.98
    acity
    0.90
    hett
    0.85
    iqu
    0.83
    Rap
    0.83
    ican
    0.81
    ional
    0.80
    itone
    0.78
    iton
    0.78
    Activations Density 0.006%

    No Known Activations