© 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 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. 6-RES-JB
    11. 2594
    Prev
    Next
    INDEX
    Explanations

    phrases or words enclosed in quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    quotations and phrases enclosed in quotation marks

    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
     Arn
    -0.73
     Alv
    -0.73
     wrinkles
    -0.71
     Asians
    -0.70
     Izan
    -0.70
     Elements
    -0.69
     shores
    -0.69
     Ern
    -0.69
     Debor
    -0.68
    culosis
    -0.68
    POSITIVE LOGITS
    complete
    1.16
    classic
    1.13
    significant
    1.10
    very
    1.08
    highly
    1.07
    little
    1.07
    false
    1.06
    political
    1.06
    reasonable
    1.05
    cheat
    1.05
    Activations Density 0.026%

    No Known Activations