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. 0-RES-JB
    6. 22110
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing resources or support

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "provide."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Beetle
    -0.71
    hate
    -0.68
     race
    -0.67
    _-
    -0.67
    ylum
    -0.66
    thal
    -0.64
     shader
    -0.64
     races
    -0.64
    aline
    -0.63
    baum
    -0.62
    POSITIVE LOGITS
     Prov
    4.00
    Prov
    2.27
     PROV
    1.94
    prov
    1.81
     prov
    1.73
     Provider
    1.62
    PROV
    1.38
     Provision
    1.19
     Provided
    1.15
     Providence
    1.11
    Activations Density 0.012%

    No Known Activations