Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 7-RES-JB
    6. 11891
    Prev
    Next
    INDEX
    Explanations

    words related to scientific disciplines and terms

    oai_token-act-pair · gpt-3.5-turbo

    words related to science and academia, particularly in physics and sociology

    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
    EStreamFrame
    -0.72
     tuna
    -0.70
     socket
    -0.67
     backfield
    -0.65
     Kodi
    -0.62
     Wellington
    -0.59
     REPL
    -0.59
     Blu
    -0.59
     weeping
    -0.57
     Cullen
    -0.57
    POSITIVE LOGITS
    icians
    1.17
    ically
    1.00
    ician
    0.98
    ICAL
    0.91
    ochemical
    0.90
    ALLY
    0.88
    odynam
    0.86
    alyst
    0.84
    odynamic
    0.83
    inery
    0.82
    Activations Density 0.107%

    No Known Activations