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. 4-RES-JB
    6. 17672
    Prev
    Next
    INDEX
    Explanations

    phone numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to phone numbers, particularly the format of 800 numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bid
    -0.79
    lict
    -0.75
    actor
    -0.72
    agn
    -0.70
    oral
    -0.69
    ributed
    -0.68
    alez
    -0.67
    rero
    -0.67
    par
    -0.66
    oles
    -0.66
    POSITIVE LOGITS
     MHz
    0.91
    989
    0.86
     msec
    0.85
    MHz
    0.79
    eenth
    0.78
    ãĥ¼ãĥĨãĤ£
    0.76
    Hz
    0.76
     kHz
    0.74
    800
    0.74
    kHz
    0.74
    Activations Density 0.014%

    No Known Activations