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. 10932
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a range or interval

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "between" and its variations

    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
    iasis
    -0.74
    der
    -0.74
    vous
    -0.74
    herty
    -0.73
    bi
    -0.72
    OGR
    -0.71
    Lev
    -0.71
    elman
    -0.69
    rav
    -0.69
    di
    -0.69
    POSITIVE LOGITS
    between
    0.77
     halves
    0.68
    ween
    0.67
     between
    0.66
     friendships
    0.66
     sexes
    0.64
     rounds
    0.62
     Between
    0.61
     genders
    0.61
     buddies
    0.60
    Activations Density 0.049%

    No Known Activations