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. 9-RES-JB
    6. 20403
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal or economic changes

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to technological and social structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ARC
    -0.62
     Bernstein
    -0.60
     Alley
    -0.59
     Noon
    -0.58
     ATT
    -0.57
     AAA
    -0.56
     spokeswoman
    -0.54
     Repair
    -0.54
     Zurich
    -0.54
     Asc
    -0.53
    POSITIVE LOGITS
     underscores
    1.21
     attest
    1.12
     reinforces
    1.12
     proves
    1.11
     suggests
    1.09
     demonstrates
    1.09
     lends
    1.07
     illustrates
    1.05
     coincided
    1.05
     coincides
    1.02
    Activations Density 0.633%

    No Known Activations