© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 258
    Prev
    Next
    INDEX
    Explanations

    phrases related to leadership and responsibility

    oai_token-act-pair · gpt-3.5-turbo

    words related to various types of artistic expression and genres

    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
    lein
    -0.65
    forge
    -0.63
    href
    -0.61
    eele
    -0.58
    oru
    -0.57
    igham
    -0.57
     Sas
    -0.55
     Vikings
    -0.53
    arth
    -0.53
     Lovecraft
    -0.53
    POSITIVE LOGITS
    anship
    0.71
    EngineDebug
    0.67
    \\\\\\\\
    0.67
    alid
    0.63
    istically
    0.62
    ESE
    0.61
    YING
    0.60
    ctors
    0.60
    rium
    0.60
    mares
    0.60
    Activations Density 0.264%

    No Known Activations