Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 2689
    Prev
    Next
    INDEX
    Explanations

    references to industrial activities or settings

    oai_token-act-pair · gpt-3.5-turbo

    references to industrial activities and developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CRIP
    -0.73
    inventoryQuantity
    -0.69
    aired
    -0.69
    criptions
    -0.68
     Recomm
    -0.65
    20439
    -0.64
    thood
    -0.63
    theless
    -0.62
    words
    -0.62
     Archdemon
    -0.62
    POSITIVE LOGITS
    ization
    1.15
    ists
    1.11
     hemp
    1.05
    izing
    1.01
    ised
    1.01
    isation
    1.00
    ist
    0.96
    izational
    0.95
    ized
    0.94
    ising
    0.92
    Activations Density 0.036%

    No Known Activations