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. 0-RES-JB
    6. 3880
    Prev
    Next
    INDEX
    Explanations

    adverbs describing the frequency of an action

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "regularly" and its synonyms

    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
     ANG
    -0.61
     Verse
    -0.61
     Illusion
    -0.58
    states
    -0.57
     misunderstanding
    -0.57
    isSpecialOrderable
    -0.57
    oldemort
    -0.55
     guess
    -0.55
     Translation
    -0.55
     confusion
    -0.55
    POSITIVE LOGITS
     regularly
    3.31
     routinely
    2.49
     frequently
    2.32
     periodically
    2.24
     constantly
    1.91
     consistently
    1.84
     occasionally
    1.81
     continually
    1.78
     frequent
    1.69
     continuously
    1.63
    Activations Density 0.014%

    No Known Activations