© 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. 1017
    Prev
    Next
    INDEX
    Explanations

    phrases related to fire or destruction

    oai_token-act-pair · gpt-3.5-turbo

    punctuated phrases and their potential implications

    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
    anton
    -0.74
     council
    -0.71
    acons
    -0.71
     resent
    -0.70
     fighters
    -0.70
     premises
    -0.70
     armour
    -0.70
     rece
    -0.70
     councils
    -0.69
     crest
    -0.69
    POSITIVE LOGITS
     Including
    1.03
     Politics
    1.02
     Them
    1.01
     Debate
    1.00
     Ages
    0.99
     Relationship
    0.99
     Month
    0.98
     Hits
    0.98
     Practices
    0.98
     Away
    0.97
    Activations Density 0.329%

    No Known Activations