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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22455
    Prev
    Next
    INDEX
    Explanations

    references to phone calls or communication over the phone

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "call" in various contexts

    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
     Fiction
    -0.68
     ferment
    -0.65
     concentration
    -0.63
     Flavoring
    -0.63
     stocking
    -0.61
     inh
    -0.61
     embr
    -0.60
     Pieces
    -0.60
     nonex
    -0.59
     temp
    -0.59
    POSITIVE LOGITS
    backs
    1.29
    igraph
    1.17
    call
    0.97
    oused
    0.92
    calling
    0.82
    outs
    0.78
    externalActionCode
    0.77
     caller
    0.75
    ouses
    0.74
     911
    0.73
    Activations Density 0.040%

    No Known Activations