© 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. 11-RES-JB
    11. 21050
    Prev
    Next
    INDEX
    Explanations

    phrases related to leaving an impact or impression

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating absence, vacancy, or a negative impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uits
    -0.75
     Frequency
    -0.67
    GW
    -0.67
    scl
    -0.66
    alth
    -0.66
     Telesc
    -0.64
    FactoryReloaded
    -0.63
    anta
    -0.63
    Attempts
    -0.62
    adian
    -0.61
    POSITIVE LOGITS
     footprints
    1.25
     impression
    1.22
     imprint
    1.21
     residue
    1.18
     trail
    1.18
     mark
    1.14
     scars
    1.14
     gaping
    1.11
     voic
    1.07
     footprint
    1.02
    Activations Density 0.120%

    No Known Activations