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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7-RES-JB
    6. 5373
    Prev
    Next
    INDEX
    Explanations

    phrases indicating familiarity or habituation to a particular situation or experience

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases involving the concept of being accustomed to something

    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
    backer
    -0.79
    asus
    -0.77
    odiac
    -0.69
    akura
    -0.67
     embarked
    -0.66
    ighters
    -0.66
    Ak
    -0.64
    aurus
    -0.64
    hesis
    -0.64
    fam
    -0.64
    POSITIVE LOGITS
     seeing
    1.08
     hearing
    0.90
     inflicting
    0.77
     dealing
    0.77
     treating
    0.73
     torment
    0.73
     withstand
    0.72
     watching
    0.71
     silence
    0.71
     solving
    0.71
    Activations Density 0.044%

    No Known Activations