© 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. 7-RES-JB
    11. 24165
    Prev
    Next
    INDEX
    Explanations

    contact information such as phone numbers and departments

    oai_token-act-pair · gpt-3.5-turbo

    contact information for customer service and help resources

    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
     stacking
    -0.71
     delight
    -0.67
     losers
    -0.65
     RAID
    -0.64
     masks
    -0.64
     gravy
    -0.62
     stacked
    -0.62
     floats
    -0.62
     dism
    -0.61
     dominates
    -0.61
    POSITIVE LOGITS
    Email
    1.03
    contact
    0.96
     Contact
    0.96
    email
    0.94
    Phone
    0.89
    Website
    0.85
     toll
    0.85
    ername
    0.84
     contact
    0.84
    Fax
    0.83
    Activations Density 0.196%

    No Known Activations