© 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. 3197
    Prev
    Next
    INDEX
    Explanations

    phrases related to the usage or application of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "used in" within various contexts

    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
    76561
    -0.72
    govtrack
    -0.69
     Niet
    -0.64
    jri
    -0.64
    ydia
    -0.63
    oldown
    -0.62
    rio
    -0.61
    hesda
    -0.61
    fff
    -0.61
    zyme
    -0.60
    POSITIVE LOGITS
     conjunction
    1.18
     lieu
    1.05
     emergencies
    0.84
     disguise
    0.81
    ordinate
    0.79
     tandem
    0.79
     everyday
    0.78
     vain
    0.77
     practise
    0.72
    essen
    0.71
    Activations Density 0.169%

    No Known Activations