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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-RES-JB
    6. 10563
    Prev
    Next
    INDEX
    Explanations

    specific line numbers in a document

    oai_token-act-pair · gpt-3.5-turbo

    numeric values, particularly in the context of measurements or labels

    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
    ogy
    -0.76
    ensen
    -0.69
    anyon
    -0.67
    ¬¼
    -0.63
    adin
    -0.62
    VEN
    -0.60
    anon
    -0.58
    ong
    -0.58
    adow
    -0.58
    quickShipAvailable
    -0.58
    POSITIVE LOGITS
    34
    1.10
    33
    1.08
    35
    1.07
    31
    1.07
    29
    1.06
    36
    1.05
    32
    1.01
    28
    0.99
    37
    0.98
     34
    0.97
    Activations Density 0.058%

    No Known Activations