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. 6117
    Prev
    Next
    INDEX
    Explanations

    phone-related words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "phone."

    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
    rix
    -1.13
    urities
    -0.73
    iverpool
    -0.71
    liga
    -0.70
     Inher
    -0.70
    nesday
    -0.69
     Wem
    -0.65
    alis
    -0.65
    xual
    -0.64
    riks
    -0.64
    POSITIVE LOGITS
     phones
    0.88
     phone
    0.85
    ysis
    0.84
     contacts
    0.84
    phones
    0.83
    gap
    0.81
     booths
    0.79
     booth
    0.78
     handset
    0.77
     calls
    0.74
    Activations Density 0.022%

    No Known Activations