© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 1069
    Prev
    Next
    INDEX
    Explanations

    words related to themes of evidence and support

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating quantities or rates of evidence and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Liberation
    -0.67
     fundament
    -0.67
     cessation
    -0.65
     arrang
    -0.63
     Zionism
    -0.63
    Alert
    -0.62
    Pal
    -0.62
     Situation
    -0.61
    creation
    -0.58
     imposition
    -0.58
    POSITIVE LOGITS
     populated
    0.87
    alions
    0.82
     copies
    0.79
    dozen
    0.76
     litres
    0.74
    ixel
    0.70
    users
    0.70
    percent
    0.69
    iter
    0.67
     gallons
    0.66
    Activations Density 0.364%

    No Known Activations