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. 9-RES-JB
    6. 18724
    Prev
    Next
    INDEX
    Explanations

    information related to music releases (albums, EPs, singles) and their timelines

    oai_token-act-pair · gpt-3.5-turbo

    references to new music releases and upcoming albums

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administ
    -0.76
     administrators
    -0.71
    UTC
    -0.70
    localhost
    -0.69
     reacts
    -0.68
    ISO
    -0.68
     moderators
    -0.66
    gpu
    -0.66
    hunt
    -0.66
    Administ
    -0.65
    POSITIVE LOGITS
     album
    1.36
     autobiography
    1.33
     memoir
    1.30
     novel
    1.27
     anthology
    1.19
     thriller
    1.18
     masterpiece
    1.18
     autobi
    1.17
     albums
    1.14
     book
    1.08
    Activations Density 0.437%

    No Known Activations