© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 10052
    Prev
    Next
    INDEX
    Explanations

    words related to the city of Düsseldorf

    oai_token-act-pair · gpt-3.5-turbo

    the word "se" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kirin
    -0.60
     liking
    -0.60
    hetti
    -0.60
     shorth
    -0.59
     crooked
    -0.55
    STER
    -0.55
     charred
    -0.55
    iatus
    -0.55
     agon
    -0.55
    ousel
    -0.55
    POSITIVE LOGITS
    mination
    1.05
    eker
    1.01
    ggles
    0.95
    gger
    0.93
    ptic
    0.93
    vier
    0.93
    ld
    0.92
    lled
    0.91
    gur
    0.91
    ffect
    0.88
    Activations Density 0.040%

    No Known Activations