© 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. 15774
    Prev
    Next
    INDEX
    Explanations

    phrases indicating motivation or purpose

    oai_token-act-pair · gpt-3.5-turbo

    the word "for" used 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
    river
    -0.72
    uart
    -0.67
    riger
    -0.65
    fleet
    -0.65
     Forth
    -0.63
    aware
    -0.62
    909
    -0.61
     Caption
    -0.60
    inese
    -0.59
    antine
    -0.59
    POSITIVE LOGITS
     reasons
    1.27
     purposes
    1.10
     sake
    1.09
     example
    1.04
    geries
    0.99
    gotten
    0.99
    bidden
    0.97
     awhile
    0.95
     eternity
    0.95
     instance
    0.95
    Activations Density 0.193%

    No Known Activations