© 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. 2236
    Prev
    Next
    INDEX
    Explanations

    words related to shared concepts or resources

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "common" in 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
    agate
    -0.82
    asus
    -0.78
    hyde
    -0.78
    gur
    -0.75
    resy
    -0.72
    zona
    -0.70
    endas
    -0.69
    otos
    -0.68
    enda
    -0.68
     fres
    -0.68
    POSITIVE LOGITS
    wealth
    1.48
    alities
    1.27
    ality
    1.12
     denomin
    1.10
    places
    1.06
     ancestor
    0.98
    ensical
    0.96
     decency
    0.89
    place
    0.88
     misconception
    0.74
    Activations Density 0.027%

    No Known Activations