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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 4910
    Prev
    Next
    INDEX
    Explanations

    phone numbers or actions related to calling authorities for criminal or emergency situations

    oai_token-act-pair · gpt-3.5-turbo

    requests for people to provide information by making phone calls

    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
     Flavoring
    -0.71
    _-
    -0.68
     embr
    -0.68
    inth
    -0.67
    bilt
    -0.66
    alde
    -0.66
    fruit
    -0.66
    ottest
    -0.64
    olars
    -0.64
    izontal
    -0.62
    POSITIVE LOGITS
     911
    1.08
    call
    0.97
    backs
    0.95
    igraph
    0.86
     caller
    0.82
     Call
    0.81
     Nightmares
    0.80
    Call
    0.79
     attention
    0.75
     hotline
    0.74
    Activations Density 0.054%

    No Known Activations