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. 11-RES-JB
    6. 8935
    Prev
    Next
    INDEX
    Explanations

    addresses and contact information

    oai_token-act-pair · gpt-3.5-turbo

    names of locations and geographic identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rious
    -0.68
     Witcher
    -0.66
     Grave
    -0.63
    rian
    -0.60
     cannibal
    -0.59
     Crus
    -0.59
    vous
    -0.58
     portfolios
    -0.58
    ories
    -0.57
    ibles
    -0.56
    POSITIVE LOGITS
    Phone
    0.92
    Tel
    0.91
     98
    0.89
     Phone
    0.85
    ;;;;;;;;;;;;
    0.84
     701
    0.83
     Telephone
    0.81
     980
    0.79
     Directions
    0.77
     920
    0.76
    Activations Density 0.087%

    No Known Activations