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. 7-RES-JB
    6. 19997
    Prev
    Next
    INDEX
    Explanations

    cities or locations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of places and specific entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mechanically
    -0.68
     scra
    -0.67
     fielding
    -0.65
     bearer
    -0.65
     academ
    -0.63
     identifying
    -0.62
     mature
    -0.61
     dearly
    -0.61
     authentic
    -0.60
     favorable
    -0.60
    POSITIVE LOGITS
    phia
    0.98
    icz
    0.97
    nir
    0.91
    ai
    0.91
    uy
    0.89
    hai
    0.86
    ka
    0.85
    ia
    0.83
    tein
    0.83
    ui
    0.82
    Activations Density 0.382%

    No Known Activations