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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 4540
    Prev
    Next
    INDEX
    Explanations

    sports statistics and performance metrics related to ice hockey goaltenders

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    statistics related to sports performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    sonian
    -0.73
    actionDate
    -0.71
    ril
    -0.64
    sym
    -0.64
     srfAttach
    -0.61
    onym
    -0.61
     Letters
    -0.59
    wave
    -0.59
    bass
    -0.59
    ozy
    -0.58
    POSITIVE LOGITS
     conceded
    1.25
     allowed
    1.23
     scored
    1.21
     surrendered
    1.16
     per
    1.08
     gained
    1.08
     played
    1.06
     consumed
    1.00
     permitted
    0.99
     saved
    0.98
    Activations Density 0.115%

    No Known Activations