© 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 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. 20585
    Prev
    Next
    INDEX
    Explanations

    locations and regions mentioned in news articles or reports

    oai_token-act-pair · gpt-3.5-turbo

    geographical locations and administrative divisions

    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
     moms
    -0.77
    Jones
    -0.68
    STAT
    -0.68
    erity
    -0.68
    urers
    -0.63
    ormonal
    -0.62
    ober
    -0.62
    Miller
    -0.62
    ometric
    -0.62
    arget
    -0.62
    POSITIVE LOGITS
    fecture
    0.93
     âĵĺ
    0.89
     Senegal
    0.86
     southeast
    0.86
     northeast
    0.82
     northwest
    0.81
    clave
    0.80
    near
    0.80
     suburb
    0.78
     Borough
    0.76
    Activations Density 0.147%

    No Known Activations