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. 11470
    Prev
    Next
    INDEX
    Explanations

    instances where the word "separate" is used

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "separate."

    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
    enos
    -0.88
    eno
    -0.84
     Beans
    -0.77
    Ö¼
    -0.77
    iker
    -0.69
     Briggs
    -0.68
    someone
    -0.67
    amac
    -0.66
    Des
    -0.65
    emi
    -0.64
    POSITIVE LOGITS
     separate
    0.95
     detach
    0.81
     sexes
    0.81
     sides
    0.75
    iating
    0.73
    otom
    0.72
     batches
    0.72
     distinct
    0.72
    ively
    0.71
     halves
    0.71
    Activations Density 0.015%

    No Known Activations