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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 9002
    Prev
    Next
    INDEX
    Explanations

    mentions of soundtracks

    oai_token-act-pair · gpt-3.5-turbo

    references to soundtracks and music compositions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    doms
    -0.86
    atan
    -0.83
    raham
    -0.83
    abad
    -0.76
    arah
    -0.73
    keye
    -0.71
    eem
    -0.70
    hips
    -0.67
    vati
    -0.66
    rieve
    -0.64
    POSITIVE LOGITS
     soundtrack
    1.10
    tracks
    0.81
     composer
    0.80
     playlist
    0.79
     louder
    0.76
    urally
    0.75
     lyrics
    0.73
     accompan
    0.73
     thereto
    0.71
    stress
    0.68
    Activations Density 0.036%

    No Known Activations