© 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. 7-RES-JB
    6. 19452
    Prev
    Next
    INDEX
    Explanations

    verbs ending in 've'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ve" or its derivations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GOODMAN
    -0.74
    olicy
    -0.70
    £ı
    -0.69
    assian
    -0.67
    artifacts
    -0.66
     showers
    -0.63
    ological
    -0.63
    selves
    -0.62
    ologically
    -0.60
    ģĸ
    -0.59
    POSITIVE LOGITS
    illance
    1.22
    ttes
    1.15
    mber
    1.14
    tt
    1.05
    ggie
    1.02
    llers
    1.00
    tta
    0.98
    tted
    0.98
    ller
    0.98
    lla
    0.96
    Activations Density 0.036%

    No Known Activations