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. 253
    Prev
    Next
    INDEX
    Explanations

    references to the music streaming service Spotify

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Spotify and related music streaming terms

    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
    otype
    -0.78
    orate
    -0.76
    eling
    -0.75
    esan
    -0.72
    eki
    -0.71
    otypes
    -0.70
    omsday
    -0.69
    oard
    -0.68
    otyp
    -0.68
    haw
    -0.66
    POSITIVE LOGITS
     playlist
    0.99
     Spotify
    0.91
    ify
    0.76
     Songs
    0.75
     Concert
    0.74
    ãĤ§
    0.73
     Moz
    0.72
     Plays
    0.71
    Spot
    0.70
    ãĥ¤
    0.70
    Activations Density 0.024%

    No Known Activations