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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 12312
    Prev
    Next
    INDEX
    Explanations

    comma-separated lists within sentences

    oai_token-act-pair · gpt-3.5-turbo

    punctuation or commas in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VERTISEMENT
    -0.74
    èĢħ
    -0.70
    rance
    -0.65
    rage
    -0.60
    ãģ®
    -0.59
    kie
    -0.59
    oire
    -0.59
    yna
    -0.59
    board
    -0.58
    enter
    -0.58
    POSITIVE LOGITS
     nevertheless
    1.21
     nonetheless
    1.03
    Downloadha
    0.94
     alas
    0.84
     fortunately
    0.78
     interestingly
    0.74
    tons
    0.73
    chery
    0.72
     suffice
    0.72
     insofar
    0.70
    Activations Density 0.274%

    No Known Activations