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

    Neuronpedia

    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. 9-RES-JB
    11. 15669
    Prev
    Next
    INDEX
    Explanations

    phrases related to processes or actions

    oai_token-act-pair · gpt-3.5-turbo

    feedback and evaluation of performance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ggles
    -0.69
     Adds
    -0.68
    ctuary
    -0.67
     awaits
    -0.63
     HERE
    -0.60
    erenn
    -0.59
     WATCH
    -0.58
     prepares
    -0.58
     Recently
    -0.57
    hovah
    -0.57
    POSITIVE LOGITS
     lacked
    1.12
     mattered
    1.04
     tended
    1.02
     depended
    1.00
     hadn
    1.00
     consisted
    0.98
     had
    0.98
     seemed
    0.96
     weren
    0.95
     knew
    0.95
    Activations Density 2.492%

    No Known Activations