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. 0-RES-JB
    6. 24565
    Prev
    Next
    INDEX
    Explanations

    phrases related to sound and auditory senses

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "sounds" in various contexts

    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
    verage
    -0.68
    ahime
    -0.64
    Ĥİ
    -0.63
    idas
    -0.62
    gress
    -0.62
     Juda
    -0.62
     thereof
    -0.61
     vend
    -0.61
    secut
    -0.61
    endi
    -0.60
    POSITIVE LOGITS
     sounds
    3.70
     Sounds
    2.64
    Sounds
    2.52
     sound
    2.41
     sounded
    2.36
     noises
    2.15
    sound
    1.88
     smells
    1.82
     sounding
    1.77
    Sound
    1.59
    Activations Density 0.017%

    No Known Activations