© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 4908
    Prev
    Next
    INDEX
    Explanations

    social media commands to follow

    oai_token-act-pair · gpt-3.5-turbo

    references to social media following or encouragement to follow accounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fabric
    -0.65
     spec
    -0.64
    pole
    -0.64
    ably
    -0.62
     bargaining
    -0.61
     frankly
    -0.60
     stuffing
    -0.60
    ling
    -0.59
     penny
    -0.59
     goose
    -0.59
    POSITIVE LOGITS
     Follow
    3.57
    Follow
    2.12
    follow
    1.82
     follow
    1.80
     Following
    1.20
    ollower
    1.18
     Subscribe
    1.18
    LLOW
    1.14
     Become
    1.13
     followed
    1.13
    Activations Density 0.015%

    No Known Activations