© 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. 16252
    Prev
    Next
    INDEX
    Explanations

    requests for engagement or feedback

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, particularly periods and promotional language inviting engagement

    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
     acute
    -0.81
     brake
    -0.67
     thrust
    -0.66
     acquired
    -0.65
     acquisitions
    -0.63
     dism
    -0.63
     resisted
    -0.63
    ructose
    -0.62
    quartered
    -0.61
     strand
    -0.61
    POSITIVE LOGITS
     Otherwise
    1.37
     Alternatively
    1.33
     Thanks
    1.25
     Thank
    1.24
    Otherwise
    1.19
    Alternatively
    1.13
    Thank
    1.10
    Thanks
    1.07
     Email
    1.04
     Please
    1.02
    Activations Density 0.143%

    No Known Activations