© 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. 17702
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "junk" at different activation levels

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "unk," suggesting a focus on unspecified or unknown entities or 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
    voy
    -0.76
    APH
    -0.64
     expressive
    -0.63
     flare
    -0.60
     hor
    -0.60
     unintended
    -0.59
     flared
    -0.58
    effective
    -0.58
    orsi
    -0.57
     latitude
    -0.56
    POSITIVE LOGITS
    buster
    1.12
    geon
    1.04
    irk
    0.97
    rat
    0.94
    etsu
    0.91
    busters
    0.91
    ernel
    0.90
    regate
    0.90
    lift
    0.89
    ett
    0.88
    Activations Density 0.020%

    No Known Activations