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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 8-RES-JB
    6. 23142
    Prev
    Next
    INDEX
    Explanations

    names of people or places

    oai_token-act-pair · gpt-3.5-turbo

    names and titles associated with music, specifically artists, bands, and their works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tremend
    -0.77
     sophistic
    -0.69
    ccording
    -0.68
     reconc
    -0.68
     perspect
    -0.66
     helic
    -0.64
    actionDate
    -0.63
     nerds
    -0.61
    ailability
    -0.61
     psychiat
    -0.60
    POSITIVE LOGITS
     Jr
    1.12
    Jr
    0.88
     III
    0.85
     ..............
    0.79
    steen
    0.78
     II
    0.77
    berry
    0.73
    vich
    0.72
    yk
    0.71
    _-_
    0.71
    Activations Density 0.231%

    No Known Activations