© 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. 0-RES-JB
    11. 11654
    Prev
    Next
    INDEX
    Explanations

    mentions of calves and related activities or contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of calves and physical injuries related to hamstrings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rez
    -0.85
    âĺħ
    -0.77
    Kit
    -0.73
     RU
    -0.70
    Plot
    -0.70
     Jin
    -0.67
     Sunshine
    -0.67
    obs
    -0.67
     Kon
    -0.67
    rir
    -0.66
    POSITIVE LOGITS
     calf
    3.90
     calves
    2.99
     thigh
    2.17
     hamstring
    2.09
     groin
    1.94
     ankle
    1.66
     Achilles
    1.66
     thighs
    1.42
     tendon
    1.37
     forearm
    1.34
    Activations Density 0.032%

    No Known Activations