© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6-RES-JB
    11. 16656
    Prev
    Next
    INDEX
    Explanations

    action words indicating changes, improvements, or necessary steps to be taken

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate actions or conditions related to responsibility and requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    natureconservancy
    -0.73
     huh
    -0.63
     Hamb
    -0.60
    ahead
    -0.60
    idae
    -0.59
    ohan
    -0.58
     bothered
    -0.58
    Tracker
    -0.58
     badass
    -0.58
    yt
    -0.56
    POSITIVE LOGITS
    uay
    0.70
    "]=>
    0.70
    sole
    0.63
    ŃĶ
    0.62
    };
    0.61
    isse
    0.60
    kinson
    0.60
    eely
    0.59
    ril
    0.59
    olith
    0.58
    Activations Density 0.390%

    No Known Activations