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. 0-RES-JB
    6. 3851
    Prev
    Next
    INDEX
    Explanations

    phrases related to scenes or settings in a visual context

    oai_token-act-pair · gpt-3.5-turbo

    references to various backdrops or settings in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    UU
    -0.68
    ards
    -0.64
    lich
    -0.63
     Effective
    -0.60
    erk
    -0.59
     obe
    -0.58
    amin
    -0.58
    bra
    -0.56
     functionally
    -0.56
     grants
    -0.56
    POSITIVE LOGITS
     backdrop
    4.39
     background
    1.85
     foreground
    1.26
     Background
    1.25
     backgrounds
    1.23
    background
    1.15
     centerpiece
    1.12
     juxtap
    1.09
     soundtrack
    1.06
     accompan
    1.05
    Activations Density 0.018%

    No Known Activations