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. 15144
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "at some point"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific moments or instances

    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
    avorite
    -0.71
    atts
    -0.70
    rek
    -0.66
    uno
    -0.63
     twins
    -0.62
     pancakes
    -0.61
    ords
    -0.60
    little
    -0.59
    rats
    -0.59
    anders
    -0.58
    POSITIVE LOGITS
    upon
    0.76
    point
    0.75
     onwards
    0.74
    points
    0.73
    abouts
    0.70
    acle
    0.69
     climax
    0.68
     onward
    0.67
     culminating
    0.66
    endment
    0.66
    Activations Density 0.027%

    No Known Activations