© 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. 2-RES-JB
    11. 23360
    Prev
    Next
    INDEX
    Explanations

    words related to importance and necessity

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating necessity or urgency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    llah
    -0.89
    stood
    -0.75
    hips
    -0.72
    creen
    -0.71
    icas
    -0.70
    essee
    -0.69
    aido
    -0.69
    vae
    -0.68
    agues
    -0.67
    chel
    -0.67
    POSITIVE LOGITS
     imperative
    1.46
     necessity
    0.88
     nexus
    0.85
     ende
    0.80
     requirement
    0.76
     prerequisite
    0.76
     precaution
    0.75
     destro
    0.75
     coupling
    0.72
     tyr
    0.72
    Activations Density 0.004%

    No Known Activations