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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 10957
    Prev
    Next
    INDEX
    Explanations

    words related to astronomy

    oai_token-act-pair · gpt-3.5-turbo

    terms related to astronomy and astronomical organizations

    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
     Dug
    -0.73
    anwhile
    -0.71
     Feld
    -0.69
     Fargo
    -0.69
     confir
    -0.66
    nir
    -0.66
    die
    -0.64
     Snyder
    -0.64
    BACK
    -0.62
     +++
    -0.62
    POSITIVE LOGITS
    omical
    1.35
    autical
    1.16
    omy
    1.10
    auts
    0.99
    omic
    0.92
    mosp
    0.90
    aut
    0.87
    igmatic
    0.87
    eteen
    0.84
    omore
    0.84
    Activations Density 0.016%

    No Known Activations