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. 8-RES-JB
    6. 19877
    Prev
    Next
    INDEX
    Explanations

    the word "Throughout"

    oai_token-act-pair · gpt-3.5-turbo

    the word "throughout" and its variations in the context of temporal continuity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tu
    -0.77
    ku
    -0.70
    elling
    -0.69
    ge
    -0.67
    umo
    -0.67
    GE
    -0.66
    Reviewer
    -0.66
    irs
    -0.66
    potion
    -0.66
    JV
    -0.64
    POSITIVE LOGITS
     eternity
    0.88
     adolescence
    0.74
     stages
    0.72
     swat
    0.71
     infancy
    0.71
     Europe
    0.70
     phases
    0.69
    orthern
    0.67
     adolesc
    0.67
     history
    0.67
    Activations Density 0.033%

    No Known Activations