© 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. 14177
    Prev
    Next
    INDEX
    Explanations

    references to work activities and local contractors participating in energy upgrades

    oai_token-act-pair · gpt-3.5-turbo

    sentences with punctuation marks and emphatic statements

    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
     retained
    -0.84
     successor
    -0.75
    withstanding
    -0.75
     superior
    -0.74
     relinqu
    -0.74
     preference
    -0.74
     authorized
    -0.73
    ozyg
    -0.72
     completed
    -0.72
     permitted
    -0.71
    POSITIVE LOGITS
     Including
    1.36
     Especially
    1.36
     Lots
    1.23
     Everywhere
    1.16
     Sometimes
    1.11
     Hopefully
    1.09
    Especially
    1.07
     Particularly
    1.07
     Some
    1.04
     They
    1.03
    Activations Density 0.617%

    No Known Activations