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. 344
    Prev
    Next
    INDEX
    Explanations

    phrases related to organization and structure

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to systematic organization or arrangement

    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
     badge
    -0.73
     Removal
    -0.72
     Deaths
    -0.71
    Mi
    -0.68
    window
    -0.67
     removal
    -0.67
     lashes
    -0.66
    intage
    -0.65
     Glow
    -0.64
    knife
    -0.64
    POSITIVE LOGITS
     structured
    2.08
     fortunate
    1.74
     privileged
    1.55
    nered
    1.26
     disciplined
    1.19
     restruct
    1.07
     blessed
    1.06
     sheltered
    1.05
     condensed
    1.00
     crystall
    0.98
    Activations Density 0.051%

    No Known Activations