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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 20915
    Prev
    Next
    INDEX
    Explanations

    phrases indicating purpose or intention

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve intentions or purposes expressed by the word "to."

    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
    interstitial
    -0.71
     Participation
    -0.64
     texted
    -0.63
    SPONSORED
    -0.61
     NCT
    -0.60
    hern
    -0.60
     Born
    -0.59
     Minutes
    -0.59
     attributed
    -0.59
    Ī
    -0.59
    POSITIVE LOGITS
    brate
    0.97
     celebrate
    0.88
    farious
    0.81
     prove
    0.77
     uphold
    0.76
    vironment
    0.76
     defend
    0.76
    bernatorial
    0.76
    odo
    0.75
    TEXTURE
    0.75
    Activations Density 0.100%

    No Known Activations