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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-RES-JB
    6. 10745
    Prev
    Next
    INDEX
    Explanations

    words related to timekeeping devices or references to a sequence of events

    oai_token-act-pair · gpt-3.5-turbo

    the term "chronicle" or variations of it, indicating references to narratives or historical accounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AAAA
    -0.83
    aa
    -0.79
    acho
    -0.72
    uka
    -0.72
    AAA
    -0.67
    lying
    -0.67
    FP
    -0.66
    abba
    -0.66
    MU
    -0.66
    ceivable
    -0.65
    POSITIVE LOGITS
     chron
    3.98
     Chron
    2.20
    chron
    2.16
     chronological
    2.11
     timeline
    1.28
     narr
    1.25
     histor
    1.25
     Timeline
    1.22
     contempor
    1.19
     CHR
    1.19
    Activations Density 0.023%

    No Known Activations