© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 6892
    Prev
    Next
    INDEX
    Explanations

    references to the location "Kobani"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the town of Kobani

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interstitial
    -0.82
    âĸ¬
    -0.79
    xual
    -0.75
    MENT
    -0.72
    EMENT
    -0.71
    âĸ¬âĸ¬
    -0.68
    åħī
    -0.65
    WAYS
    -0.64
     Clintons
    -0.63
     vested
    -0.62
    POSITIVE LOGITS
     Kob
    1.10
    lyak
    0.90
    rien
    0.88
    istani
    0.85
    assed
    0.84
    ani
    0.84
    asaki
    0.82
    arag
    0.81
    iak
    0.81
    keye
    0.81
    Activations Density 0.004%

    No Known Activations