© 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. 13416
    Prev
    Next
    INDEX
    Explanations

    sports teams' names

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns or names related to sports teams

    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
    judicial
    -0.73
    lements
    -0.70
    schild
    -0.66
     Galile
    -0.64
     embodiments
    -0.64
    cells
    -0.62
    osponsors
    -0.61
     tragedies
    -0.61
     srfAttach
    -0.61
     fert
    -0.60
    POSITIVE LOGITS
    '
    1.04
    heet
    0.89
    hirt
    0.89
    hift
    0.88
     Athletic
    0.86
     mascot
    0.86
     Athletics
    0.84
    warm
    0.83
    peed
    0.81
    Army
    0.79
    Activations Density 0.078%

    No Known Activations