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. 2-RES-JB
    6. 2111
    Prev
    Next
    INDEX
    Explanations

    names or entities listed together as part of a group

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uta
    -0.73
    :(
    -0.72
    bugs
    -0.71
    natureconservancy
    -0.67
    atical
    -0.66
    poke
    -0.64
    hub
    -0.63
    blems
    -0.63
    ump
    -0.63
    Ĥİ
    -0.63
    POSITIVE LOGITS
     thence
    0.89
     consequently
    0.85
     vice
    0.84
     optionally
    0.84
     assorted
    0.83
     then
    0.83
     therefore
    0.82
     possibly
    0.81
     thus
    0.78
     etc
    0.77
    Activations Density 0.704%

    No Known Activations