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. 20578
    Prev
    Next
    INDEX
    Explanations

    pronouns 'them', focused on when they are preceded by a specific number in numerical context

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the word "them" in various contexts

    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
     RTX
    -0.82
    mire
    -0.71
    Limit
    -0.63
    Pause
    -0.62
     Union
    -0.61
    politics
    -0.60
     Farn
    -0.59
    =-=-
    -0.59
    gg
    -0.59
    00000
    -0.58
    POSITIVE LOGITS
    atic
    0.98
    alian
    0.86
    atically
    0.84
     succeeded
    0.83
     perished
    0.78
     survives
    0.78
     involved
    0.74
     originated
    0.74
     lasted
    0.72
     selves
    0.72
    Activations Density 0.040%

    No Known Activations