© 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. 17740
    Prev
    Next
    INDEX
    Explanations

    mentions of a concept that involves diversity or multiple aspects

    oai_token-act-pair · gpt-3.5-turbo

    references to multiplicity or multiple entities

    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
     pounding
    -0.71
     knock
    -0.69
     Roundup
    -0.66
     chilling
    -0.66
     knocking
    -0.66
     Warden
    -0.64
     rack
    -0.64
     Mum
    -0.64
     Wolves
    -0.63
     repression
    -0.63
    POSITIVE LOGITS
    icol
    1.56
    ilingual
    1.44
    ilateral
    1.40
    imedia
    1.34
    itud
    1.30
    ivariate
    1.27
    icultural
    1.24
    ivalent
    1.22
    inational
    1.22
    ipolar
    1.22
    Activations Density 0.025%

    No Known Activations