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

    Neuronpedia

    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. 9543
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions or abilities of individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "can."

    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
     Federation
    -0.66
     APPLIC
    -0.65
     rejection
    -0.64
     striving
    -0.61
     excluding
    -0.60
    soDeliveryDate
    -0.58
     revision
    -0.58
     following
    -0.58
     Shipping
    -0.58
     Strikes
    -0.58
    POSITIVE LOGITS
    't
    1.74
    berra
    1.29
    adian
    1.27
    isters
    1.20
     afford
    1.09
    ister
    1.07
    NOT
    1.05
     attest
    1.04
    nery
    0.96
    asta
    0.92
    Activations Density 0.188%

    No Known Activations