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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    6. 433
    Prev
    Next
    INDEX
    Explanations

    calls to action for sharing content with others

    oai_token-act-pair · gpt-3.5-turbo

    phrases advocating for sharing with others

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

    No Comments

    Negative Logits
    ischer
    -0.81
    ©¶æ¥µ
    -0.77
    itute
    -0.66
    ouf
    -0.65
     reviewed
    -0.65
    ovich
    -0.64
    hemat
    -0.64
    orah
    -0.63
    chin
    -0.62
    sylvania
    -0.61
    POSITIVE LOGITS
     regards
    1.17
     regard
    1.09
    stood
    1.00
    draw
    0.93
     impunity
    0.92
     respect
    0.88
     dignity
    0.81
     Pastebin
    0.79
     srfAttach
    0.77
     us
    0.75
    Activations Density 0.130%

    No Known Activations