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. 5-RES-JB
    6. 13901
    Prev
    Next
    INDEX
    Explanations

    hyphenated phrases where the second word is a verb

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the phrase "cut" in negative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Burr
    -0.69
     Chambers
    -0.69
     Confederation
    -0.68
     Imran
    -0.66
     Moj
    -0.66
     KN
    -0.64
     throats
    -0.64
     Lod
    -0.61
     revised
    -0.61
     hemisphere
    -0.61
    POSITIVE LOGITS
    based
    1.26
    through
    1.09
    your
    1.08
    rate
    1.08
    level
    1.05
    to
    1.05
    type
    1.05
    luster
    1.05
    disk
    1.04
    duty
    1.02
    Activations Density 0.139%

    No Known Activations