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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10087
    Prev
    Next
    INDEX
    Explanations

    words related to sound and noise

    oai_token-act-pair · gpt-3.5-turbo

    references to noise and its impact or occurrence

    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
    opez
    -0.77
    vez
    -0.76
    innon
    -0.75
    apsed
    -0.74
    allic
    -0.71
    rive
    -0.68
    uties
    -0.67
    alions
    -0.67
    ribe
    -0.66
    onz
    -0.66
    POSITIVE LOGITS
     noise
    1.08
     noises
    0.98
     Noise
    0.95
     amplification
    0.80
     louder
    0.79
     emitting
    0.77
     mitigation
    0.76
    mouth
    0.76
     nuisance
    0.74
     leakage
    0.73
    Activations Density 0.016%

    No Known Activations