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. 8-RES-JB
    6. 15826
    Prev
    Next
    INDEX
    Explanations

    actions or events involving specific verbs related to societal issues and interactions

    oai_token-act-pair · gpt-3.5-turbo

    actions and interactions related to societal behaviors and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xtap
    -0.83
    ikk
    -0.66
     sugg
    -0.64
    omen
    -0.60
     festive
    -0.58
    oris
    -0.55
    ¯¯¯¯¯¯¯¯
    -0.54
     Divinity
    -0.53
    ousing
    -0.52
    apter
    -0.52
    POSITIVE LOGITS
     theirs
    1.31
     hers
    1.28
     ours
    1.17
     yours
    1.15
     mine
    0.96
     oneself
    0.82
     itself
    0.74
     ourselves
    0.73
     himself
    0.68
     herself
    0.67
    Activations Density 0.759%

    No Known Activations