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. 23434
    Prev
    Next
    INDEX
    Explanations

    the word "single" preceded by "every" in the text

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "every single."

    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
    olas
    -0.74
    orthy
    -0.74
    eln
    -0.71
    arty
    -0.69
    ORK
    -0.68
    ersive
    -0.68
    umbledore
    -0.66
    ual
    -0.66
    uay
    -0.65
     exha
    -0.65
    POSITIVE LOGITS
    THING
    1.12
     digits
    0.90
     digit
    0.88
    WHERE
    0.83
     goddamn
    0.79
     imaginable
    0.78
     dollar
    0.75
    thing
    0.74
    body
    0.73
     person
    0.72
    Activations Density 0.012%

    No Known Activations