© 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. 6-RES-JB
    11. 11719
    Prev
    Next
    INDEX
    Explanations

    questions or phrases related to quantity or value

    oai_token-act-pair · gpt-3.5-turbo

    the word "much" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    İĭ
    -0.95
    Ń·
    -0.87
    idon
    -0.86
    ATURES
    -0.85
    swick
    -0.81
    ivas
    -0.80
    WAYS
    -0.80
    ands
    -0.75
    èĢ
    -0.75
    zech
    -0.75
    POSITIVE LOGITS
     damage
    0.82
     money
    0.81
     attention
    0.81
     extent
    0.80
     elapsed
    0.78
     faith
    0.78
     overlap
    0.76
     fun
    0.74
     interest
    0.74
     firepower
    0.74
    Activations Density 0.026%

    No Known Activations