© 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. 5005
    Prev
    Next
    INDEX
    Explanations

    places or locations

    oai_token-act-pair · gpt-3.5-turbo

    specific punctuation marks, particularly periods and commas

    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
     dece
    -0.74
     tremend
    -0.68
    è¦ļéĨĴ
    -0.68
     everywhere
    -0.66
    isse
    -0.66
     coy
    -0.65
     mur
    -0.64
     defe
    -0.63
     revol
    -0.63
     monopol
    -0.63
    POSITIVE LOGITS
     Additionally
    1.11
    <|endoftext|>
    1.06
     Afterwards
    1.05
     However
    1.00
     Alternatively
    0.98
     Previously
    0.94
     Furthermore
    0.94
     Moreover
    0.93
     According
    0.92
     Along
    0.92
    Activations Density 0.564%

    No Known Activations