© 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 EvalsExportsinterp-engineNEWAPI 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. 11377
    Prev
    Next
    INDEX
    Explanations

    mentions of specific actions or events that have caused a significant impact or controversy

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express the occurrence of events or actions

    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
     eras
    -0.66
     Corpus
    -0.66
    hand
    -0.63
     territ
    -0.62
     remember
    -0.62
     remembers
    -0.61
     respons
    -0.61
    oit
    -0.61
     Pt
    -0.60
    walking
    -0.60
    POSITIVE LOGITS
     been
    1.21
     garnered
    1.17
    been
    1.13
     yielded
    0.96
     become
    0.96
     resulted
    0.93
     gotten
    0.93
     lasted
    0.92
     sparked
    0.91
     begun
    0.90
    Activations Density 0.222%

    No Known Activations