© 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. 10-RES-JB
    11. 12779
    Prev
    Next
    INDEX
    Explanations

    phrases related to chemistry and chemical elements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to chemistry and chemical science

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bosnia
    -0.69
    lihood
    -0.69
     Caesar
    -0.68
     MID
    -0.67
     Eston
    -0.67
     Virgin
    -0.66
     Pew
    -0.66
     Berkshire
    -0.65
     Leia
    -0.65
     Bridgewater
    -0.65
    POSITIVE LOGITS
    icals
    1.73
    istries
    1.58
    istry
    1.55
    otherapy
    1.50
    odynamic
    1.45
    icians
    1.44
    ical
    1.42
    ically
    1.39
    odynamics
    1.36
    ists
    1.35
    Activations Density 0.033%

    No Known Activations