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. 12-RES-JB
    6. 6951
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to counterarguments or opposition viewpoints

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    instances of the word "counter" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     Minor
    -0.58
     Forge
    -0.57
     Fav
    -0.56
     Roche
    -0.54
     Bib
    -0.53
     apart
    -0.53
     Slime
    -0.53
     Jr
    -0.52
    OOD
    -0.52
    uez
    -0.52
    POSITIVE LOGITS
    intuitive
    1.39
    measures
    1.33
    intelligence
    1.23
    fact
    1.21
    balance
    1.18
    balanced
    1.17
    party
    1.16
    culture
    1.13
    cultural
    1.11
    attack
    1.09
    Activations Density 0.035%

    No Known Activations