© 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. 9557
    Prev
    Next
    INDEX
    Explanations

    contrasting descriptions or opinions between different groups of entities

    oai_token-act-pair · gpt-3.5-turbo

    references to a collective group or contrasting views among individuals

    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
    Crash
    -0.62
    Join
    -0.62
    Accessory
    -0.58
    [_
    -0.58
    \/
    -0.56
     BEFORE
    -0.55
     Encyclopedia
    -0.55
    iper
    -0.54
     LO
    -0.54
    United
    -0.53
    POSITIVE LOGITS
    hemat
    0.69
     mosqu
    0.68
    ngth
    0.66
    staking
    0.65
    ect
    0.64
    ividual
    0.64
    esters
    0.63
    inently
    0.63
     answ
    0.62
    asio
    0.60
    Activations Density 0.159%

    No Known Activations