© 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. 9767
    Prev
    Next
    INDEX
    Explanations

    phrases related to performing a specific type of work or task

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "in [number]"

    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
     learners
    -0.74
    soever
    -0.69
    casters
    -0.67
     %%
    -0.65
    username
    -0.64
    hiba
    -0.63
    worth
    -0.63
    $$
    -0.63
    hai
    -0.63
    HAEL
    -0.60
    POSITIVE LOGITS
     vain
    1.30
     unison
    1.23
     accordance
    1.21
     lieu
    1.16
     conjunction
    1.14
    clusively
    1.07
    ordinate
    1.05
     tandem
    1.05
    humane
    1.04
    clus
    1.03
    Activations Density 0.306%

    No Known Activations