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. 1-RES-JB
    6. 8527
    Prev
    Next
    INDEX
    Explanations

    mentions of voice recognition technology

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Voice" and related entities or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hers
    -0.75
    ean
    -0.71
    Ń·
    -0.69
    imes
    -0.68
    osed
    -0.66
    heid
    -0.66
    arching
    -0.65
    arding
    -0.63
     secrecy
    -0.63
    ickr
    -0.63
    POSITIVE LOGITS
     Voice
    1.21
    voice
    1.05
    Voice
    0.93
    Dialogue
    0.85
    caster
    0.82
     recorder
    0.82
     Voices
    0.82
    Player
    0.80
     Vo
    0.79
     voic
    0.78
    Activations Density 0.005%

    No Known Activations