© 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. 13907
    Prev
    Next
    INDEX
    Explanations

    phrases related to objects or substances that are recyclable

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the word "pile" and related terms

    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
    OND
    -0.68
     tremend
    -0.67
    /+
    -0.64
     Jarrett
    -0.64
    -|
    -0.61
    iannopoulos
    -0.59
     Rupert
    -0.57
    ITED
    -0.57
    akuya
    -0.57
    Sanders
    -0.57
    POSITIVE LOGITS
    ados
    1.04
    ela
    0.97
    erer
    0.92
    ings
    0.88
    adium
    0.88
    adle
    0.85
    ifer
    0.84
    asant
    0.83
    erers
    0.82
    haps
    0.82
    Activations Density 0.118%

    No Known Activations