© 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. 9-RES-JB
    11. 23336
    Prev
    Next
    INDEX
    Explanations

    phrases indicating perception or interpretation of information or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating perceptions or judgments about something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    upt
    -0.71
    tz
    -0.70
    itles
    -0.68
    named
    -0.66
    eez
    -0.66
     SUN
    -0.66
    figured
    -0.65
    ousand
    -0.65
    aiman
    -0.64
    oller
    -0.64
    POSITIVE LOGITS
     belonging
    1.00
     synonymous
    0.98
     embod
    0.88
    pires
    0.85
     favoring
    0.85
     follows
    0.84
     having
    0.83
     emblem
    0.81
     representing
    0.81
     sympt
    0.81
    Activations Density 0.069%

    No Known Activations