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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 20653
    Prev
    Next
    INDEX
    Explanations

    phrases referring to the necessity or requirement for something

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the necessity or demand for various actions or resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ora
    -0.72
    stars
    -0.71
    owned
    -0.67
    til
    -0.67
    Delta
    -0.67
    RANT
    -0.66
    Tracker
    -0.66
    lucent
    -0.66
    minus
    -0.64
     CLSID
    -0.63
    POSITIVE LOGITS
     vigilance
    0.94
     urgently
    0.91
     urgent
    0.84
     precaution
    0.83
     unanim
    0.81
     patience
    0.81
     moderation
    0.80
     caution
    0.80
     safeguard
    0.80
     urgency
    0.79
    Activations Density 0.054%

    No Known Activations