© 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. 6-RES-JB
    11. 9397
    Prev
    Next
    INDEX
    Explanations

    phrases starting with the word "a"

    oai_token-act-pair · gpt-3.5-turbo

    the indefinite articles "a" and "an"

    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
    weights
    -0.72
     TDs
    -0.70
    orest
    -0.68
    osc
    -0.68
    antes
    -0.68
    ores
    -0.67
    ometers
    -0.66
    onto
    -0.66
     favourites
    -0.66
    itiz
    -0.65
    POSITIVE LOGITS
     nutshell
    1.38
     twist
    0.90
     perverse
    0.87
     contradiction
    0.81
     brief
    0.80
     typical
    0.79
     footnote
    0.79
     statement
    0.79
     flurry
    0.79
     bizarre
    0.78
    Activations Density 0.070%

    No Known Activations