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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 10530
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to things being separate from each other

    oai_token-act-pair · gpt-3.5-turbo

    instances 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 @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ö¼
    -0.73
    eno
    -0.71
     Beans
    -0.69
    enos
    -0.65
     Bulg
    -0.64
    Des
    -0.64
    iker
    -0.63
     Zombies
    -0.62
     Reloaded
    -0.62
    vous
    -0.62
    POSITIVE LOGITS
     separate
    0.82
     stint
    0.74
     batches
    0.74
    iates
    0.73
     detach
    0.71
     identifiable
    0.71
    ively
    0.71
     entities
    0.71
     entity
    0.70
    iating
    0.70
    Activations Density 0.032%

    No Known Activations