Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 11932
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of 'controversy.'

    oai_token-act-pair · gpt-3.5-turbo

    words related to connotations and contextual meanings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    baugh
    -0.69
    TPS
    -0.68
     Norn
    -0.67
    assetsadobe
    -0.67
    terday
    -0.66
    HAEL
    -0.64
    ewski
    -0.62
     Decay
    -0.60
    lihood
    -0.60
     Kimmel
    -0.60
    POSITIVE LOGITS
    clusively
    1.17
    clave
    1.14
    gru
    1.14
    versely
    1.07
    joined
    1.05
    gres
    1.05
    formance
    1.03
    undrum
    1.02
    naissance
    1.02
    nex
    1.01
    Activations Density 0.010%

    No Known Activations