© 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. 2-RES-JB
    11. 17171
    Prev
    Next
    INDEX
    Explanations

    words related to geographical locations, specifically places ending with "port"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "port" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cumbers
    -0.67
     blinking
    -0.63
     whiff
    -0.62
     reckoning
    -0.61
     pesky
    -0.60
     precip
    -0.59
     heck
    -0.58
    hiro
    -0.58
     mood
    -0.58
    ãĥ£
    -0.57
    POSITIVE LOGITS
    folios
    1.47
    rait
    1.33
    folio
    1.32
    raits
    1.18
    port
    1.10
    ugal
    1.08
    ality
    0.88
    ocity
    0.88
    nell
    0.81
    ions
    0.78
    Activations Density 0.007%

    No Known Activations