© 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. 2211
    Prev
    Next
    INDEX
    Explanations

    scientific evidence and research-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to scientific evidence and research

    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
    ebus
    -0.74
    atra
    -0.67
     Plans
    -0.67
    cers
    -0.66
    atism
    -0.65
    angered
    -0.64
     lux
    -0.61
    awar
    -0.60
    task
    -0.59
     Fn
    -0.59
    POSITIVE LOGITS
     dispro
    1.16
     evidence
    1.11
     evid
    1.07
     proves
    1.06
     conclusive
    1.06
     attest
    1.05
     indicating
    1.05
     demonstrating
    1.05
     anecd
    1.04
     corrobor
    1.04
    Activations Density 0.247%

    No Known Activations