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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-RES-JB
    6. 20707
    Prev
    Next
    INDEX
    Explanations

    data related to time periods (e.g. years, months, semesters)

    oai_token-act-pair · gpt-3.5-turbo

    references to temporal information, particularly concerning years and events that happened within those years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vae
    -0.56
    Often
    -0.55
    bart
    -0.55
    osite
    -0.54
    elong
    -0.54
    mber
    -0.53
    THING
    -0.53
    Recently
    -0.53
     conservatism
    -0.53
     fixation
    -0.52
    POSITIVE LOGITS
     alone
    1.16
     compared
    1.10
    according
    0.96
    *.
    0.84
     according
    0.84
     thanks
    0.83
     whereas
    0.81
     totaling
    0.78
     combined
    0.77
     excluding
    0.76
    Activations Density 0.332%

    No Known Activations