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. 4589
    Prev
    Next
    INDEX
    Explanations

    pronouns ('we', 'us', 'our') and verbs related to self-reflection or self-understanding

    oai_token-act-pair · gpt-3.5-turbo

    references to collective human experiences and interactions

    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
    market
    -0.68
    Dash
    -0.66
     Saud
    -0.63
     Bust
    -0.63
     Publication
    -0.62
     RU
    -0.62
    FLAG
    -0.61
    ij士
    -0.61
    ILA
    -0.60
     Rhodes
    -0.60
    POSITIVE LOGITS
     ourselves
    1.14
     unconsciously
    1.10
     intu
    1.04
     instinctively
    1.02
     perceive
    1.02
     subconscious
    0.93
     mortals
    0.89
     gaze
    0.89
     humans
    0.88
     consume
    0.83
    Activations Density 0.264%

    No Known Activations