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. 24357
    Prev
    Next
    INDEX
    Explanations

    points of communication such as calls and emails

    oai_token-act-pair · gpt-3.5-turbo

    references to phone calls and emails

    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
    ibles
    -0.72
    azeera
    -0.69
    amina
    -0.67
    ivities
    -0.66
     Heritage
    -0.65
    enne
    -0.59
    inker
    -0.59
    alks
    -0.59
    aband
    -0.58
    arton
    -0.58
    POSITIVE LOGITS
    dylib
    0.81
     informing
    0.80
    print
    0.77
     thanking
    0.75
     recommending
    0.75
    DragonMagazine
    0.74
     notification
    0.73
     indicating
    0.71
     regarding
    0.71
    REC
    0.71
    Activations Density 0.163%

    No Known Activations