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. 6164
    Prev
    Next
    INDEX
    Explanations

    mentions of the hobbyists and their activities or community

    oai_token-act-pair · gpt-3.5-turbo

    terms related to hobbies and hobbyists

    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
     skulls
    -0.65
     curv
    -0.63
     Apostles
    -0.63
     sclerosis
    -0.63
     Ezekiel
    -0.62
    使
    -0.61
     walls
    -0.61
     Hurricanes
    -0.60
     cliffs
    -0.60
     Wick
    -0.60
    POSITIVE LOGITS
     hobby
    1.12
    reprene
    0.94
    ist
    0.92
    ists
    0.92
    istry
    0.90
    icion
    0.84
    horse
    0.83
    Shop
    0.82
    ischer
    0.82
    sonian
    0.82
    Activations Density 0.021%

    No Known Activations