© 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. 0-RES-JB
    11. 16358
    Prev
    Next
    INDEX
    Explanations

    the word "acoustics"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to acoustics and sound properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sa
    -0.64
     vein
    -0.64
     Vera
    -0.63
     Migration
    -0.62
     Indigo
    -0.61
     pages
    -0.60
    lights
    -0.60
     CI
    -0.60
     Commit
    -0.60
     Savings
    -0.59
    POSITIVE LOGITS
    oust
    4.42
    oustic
    1.57
    rax
    1.41
    ollah
    1.23
    ovember
    0.93
    ospace
    0.91
     loudspe
    0.87
    ingu
    0.87
    oÄŁ
    0.86
    adem
    0.86
    Activations Density 0.029%

    No Known Activations