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. 3-RES-JB
    6. 7344
    Prev
    Next
    INDEX
    Explanations

    words related to nighttime or darkness

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with heights or climbing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mb
    -0.76
    Wi
    -0.68
    Credits
    -0.67
    Interstitial
    -0.67
     Sigma
    -0.65
    Chan
    -0.64
     Yen
    -0.64
    Reviewed
    -0.63
     Bib
    -0.63
    NZ
    -0.62
    POSITIVE LOGITS
    etheless
    0.98
    oleon
    0.71
    stery
    0.69
    urnal
    0.68
    hawk
    0.67
    iqueness
    0.67
    arious
    0.66
     bluff
    0.66
     poker
    0.65
    ully
    0.65
    Activations Density 0.071%

    No Known Activations