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. 8-RES-JB
    6. 21666
    Prev
    Next
    INDEX
    Explanations

    word related to noise

    oai_token-act-pair · gpt-3.5-turbo

    terms related to noise and its impact or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    opez
    -0.76
    vez
    -0.73
    armac
    -0.73
    folios
    -0.70
    lege
    -0.70
    hetical
    -0.69
    erest
    -0.67
    iste
    -0.65
    olkien
    -0.64
     Lann
    -0.63
    POSITIVE LOGITS
     noise
    0.87
     emitted
    0.85
     pollution
    0.84
     emitting
    0.84
     detectors
    0.82
     detector
    0.82
     amplification
    0.82
     emanating
    0.78
     noises
    0.78
     Noise
    0.78
    Activations Density 0.041%

    No Known Activations