© 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. 13845
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical locations related to the coast

    oai_token-act-pair · gpt-3.5-turbo

    references to coastal regions and areas

    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
    sen
    -0.93
    endi
    -0.80
    ername
    -0.80
    atile
    -0.79
     Machina
    -0.75
    enger
    -0.71
    Downloadha
    -0.70
    chel
    -0.69
    chen
    -0.69
    hig
    -0.68
    POSITIVE LOGITS
     erosion
    0.93
     waters
    0.88
     waterways
    0.87
     inund
    0.85
     regions
    0.83
     areas
    0.82
     area
    0.82
     coastal
    0.81
     towns
    0.80
     wetlands
    0.79
    Activations Density 0.016%

    No Known Activations