© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 16480
    Prev
    Next
    INDEX
    Explanations

    words related to organizing or tabulating information

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Apocalypse
    -0.69
     analogy
    -0.69
     trickle
    -0.68
     mate
    -0.68
     epit
    -0.68
     veget
    -0.66
     imperson
    -0.65
     vibe
    -0.65
     Resort
    -0.65
     stare
    -0.65
    POSITIVE LOGITS
    tab
    2.81
    cur
    2.47
    search
    1.42
    mary
    1.36
    grid
    1.34
    ahead
    1.34
    dot
    1.34
    sid
    1.33
    vari
    1.26
    option
    1.25
    Activations Density 0.050%

    No Known Activations