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. 6515
    Prev
    Next
    INDEX
    Explanations

    keywords related to data storage and management

    oai_token-act-pair · gpt-3.5-turbo

    technical terminology related to data storage and processing systems

    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
    Ħ¢
    -0.82
    £
    -0.79
    iola
    -0.79
    utterstock
    -0.75
    mist
    -0.74
    iers
    -0.74
    assic
    -0.73
    taboola
    -0.72
    youtu
    -0.72
    acus
    -0.71
    POSITIVE LOGITS
     output
    0.92
     automatic
    0.89
     interpol
    0.88
     debugging
    0.86
     cursor
    0.84
     optional
    0.83
     initialization
    0.82
     optionally
    0.82
     visibility
    0.81
     foreground
    0.80
    Activations Density 0.305%

    No Known Activations