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. 16646
    Prev
    Next
    INDEX
    Explanations

    words related to time or sequence

    oai_token-act-pair · gpt-3.5-turbo

    the word "then" indicating a reference to a past time or context

    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
    toe
    -0.77
    assed
    -0.72
    ting
    -0.67
    ciplinary
    -0.62
    pace
    -0.59
    Winged
    -0.58
    icles
    -0.58
    ility
    -0.58
    ications
    -0.57
    cott
    -0.57
    POSITIVE LOGITS
    Ń·
    0.91
    emort
    0.72
    orthy
    0.71
    ratulations
    0.68
    ©¶æ
    0.67
     unfocusedRange
    0.66
    abouts
    0.66
    esar
    0.66
    ð
    0.65
    å§«
    0.65
    Activations Density 0.048%

    No Known Activations