© 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. 11735
    Prev
    Next
    INDEX
    Explanations

    instances where the text discusses ability or possibility

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "can" in various contexts, indicating ability or possibility

    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
    ULTS
    -0.67
    soever
    -0.67
     spoilers
    -0.65
    senal
    -0.64
     Actions
    -0.63
     reflections
    -0.62
     Falling
    -0.62
     Strikes
    -0.61
    quartered
    -0.60
     Sands
    -0.60
    POSITIVE LOGITS
    't
    1.52
     afford
    1.43
     convince
    1.11
     persuade
    1.01
     muster
    1.00
     manage
    0.96
     reliably
    0.93
    adian
    0.92
     tolerate
    0.89
     find
    0.89
    Activations Density 0.103%

    No Known Activations