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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 17230
    Prev
    Next
    INDEX
    Explanations

    phone numbers with area codes and dashes

    oai_token-act-pair · gpt-3.5-turbo

    contact information, including phone numbers and email addresses

    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
    bread
    -0.57
    aliation
    -0.55
    rely
    -0.54
     shape
    -0.54
     overpowered
    -0.54
     predictable
    -0.54
     stacking
    -0.52
     unsus
    -0.52
     consistency
    -0.52
     fleeing
    -0.52
    POSITIVE LOGITS
    Fax
    0.72
     978
    0.63
     CLR
    0.63
    XP
    0.62
    ifer
    0.60
    TI
    0.58
    IFIED
    0.58
    osterone
    0.58
    ulz
    0.58
    INFO
    0.58
    Activations Density 0.041%

    No Known Activations