Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7234
    Prev
    Next
    INDEX
    Explanations

    user profiles, particularly highlighting the "Profile" section

    oai_token-act-pair · gpt-3.5-turbo

    references to user profiles and blogs

    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
    pled
    -0.72
    assic
    -0.71
    nesday
    -0.70
    urers
    -0.70
    unal
    -0.70
    bnb
    -0.67
    heed
    -0.67
    footed
    -0.66
    uve
    -0.64
    abouts
    -0.64
    POSITIVE LOGITS
     Joined
    1.43
     Blog
    1.37
    Joined
    0.91
     Posts
    0.90
     DevOnline
    0.83
     Creator
    0.80
     Member
    0.79
     Managing
    0.77
     StarCraft
    0.76
     Potion
    0.76
    Activations Density 0.054%

    No Known Activations