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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 2266
    Prev
    Next
    INDEX
    Explanations

    phrases related to division or categorization

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve dividing or splitting into sections or categories

    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
    onda
    -0.71
     challeng
    -0.67
     override
    -0.67
    SPONSORED
    -0.67
     harassed
    -0.63
     intimid
    -0.63
    era
    -0.63
     bothered
    -0.63
     pressured
    -0.63
     insulted
    -0.63
    POSITIVE LOGITS
     thirds
    0.91
    clusions
    0.74
     submission
    0.72
     categories
    0.70
     Pieces
    0.67
    uild
    0.67
     adulthood
    0.67
    flows
    0.66
    ãĤ©
    0.66
    units
    0.64
    Activations Density 0.040%

    No Known Activations