© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 13251
    Prev
    Next
    INDEX
    Explanations

    contact information such as phone numbers and addresses

    oai_token-act-pair · gpt-3.5-turbo

    contact details, particularly phone numbers and the action of calling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     clips
    -0.75
     footing
    -0.71
     narrator
    -0.70
     stacked
    -0.67
     cull
    -0.67
     predictably
    -0.67
     RAID
    -0.65
     stacking
    -0.65
     clip
    -0.64
    inventoryQuantity
    -0.64
    POSITIVE LOGITS
    Phone
    1.17
    Email
    1.12
     978
    1.12
     tradem
    1.10
    Tel
    1.09
    877
    1.08
    email
    1.07
    Fax
    1.05
    866
    1.03
     212
    1.03
    Activations Density 0.250%

    No Known Activations