© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 4412
    Prev
    Next
    INDEX
    Explanations

    the word "tick" occurring with a high degree of activation, regardless of context

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "tick" and its variations, suggesting a focus on time-related or mechanical themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocally
    -0.69
     Galile
    -0.64
    pha
    -0.64
    ht
    -0.61
    pite
    -0.60
    ãģ®å
    -0.60
    ãĥ´ãĤ¡
    -0.59
     ILCS
    -0.59
     cov
    -0.58
    byss
    -0.57
    POSITIVE LOGITS
     tick
    1.05
    ering
    0.92
    tick
    0.90
    lish
    0.88
    ety
    0.86
    lers
    0.84
    ched
    0.84
    eworthy
    0.82
    ypes
    0.81
    leness
    0.80
    Activations Density 0.006%

    No Known Activations