© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 3019
    Prev
    Next
    INDEX
    Explanations

    phrases related to individual achievements or accomplishments

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "in" indicating location or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    genre
    -0.70
    oké
    -0.67
    +)
    -0.67
    information
    -0.63
     importantly
    -0.61
    riet
    -0.59
    odd
    -0.59
    meaning
    -0.59
    ritten
    -0.58
     contradictory
    -0.58
    POSITIVE LOGITS
     whom
    0.99
     Lifetime
    0.81
    etime
    0.77
     Infinite
    0.75
     Valhalla
    0.68
     1988
    0.67
     Mount
    0.67
     2007
    0.67
    pload
    0.66
     Cannes
    0.66
    Activations Density 0.303%

    No Known Activations