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. 2-RES-JB
    6. 3452
    Prev
    Next
    INDEX
    Explanations

    the word "separate" and phrases related to separating objects or entities

    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 @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =-=-=-=-=-=-=-=-
    -0.77
    WARD
    -0.72
    eno
    -0.72
    enos
    -0.72
     Beans
    -0.71
    âĺħâĺħ
    -0.69
    annis
    -0.68
     Briggs
    -0.68
    yo
    -0.67
    iker
    -0.67
    POSITIVE LOGITS
     detach
    0.92
     sexes
    0.90
    iating
    0.90
     separate
    0.90
    inguished
    0.89
    ively
    0.84
     halves
    0.84
     separ
    0.80
     sides
    0.77
    iates
    0.76
    Activations Density 0.018%

    No Known Activations