© 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. 13582
    Prev
    Next
    INDEX
    Explanations

    phrases related to energy and physical exertion

    oai_token-act-pair · gpt-3.5-turbo

    references to energy levels and the importance of energy in various contexts

    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
    ãĥīãĥ©
    -0.82
    gery
    -0.77
    ettings
    -0.76
    cott
    -0.73
    lihood
    -0.70
     Settlement
    -0.69
     Doct
    -0.68
    ournal
    -0.64
    azeera
    -0.62
    igmat
    -0.61
    POSITIVE LOGITS
     expended
    0.83
     energy
    0.81
     metabolism
    0.81
     Enhancement
    0.80
    fulness
    0.79
     powering
    0.76
     depletion
    0.76
     drinks
    0.75
     ener
    0.75
     energ
    0.75
    Activations Density 0.036%

    No Known Activations