© 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. 0-RES-JB
    11. 1215
    Prev
    Next
    INDEX
    Explanations

    words related to mental health and unstable behavior

    oai_token-act-pair · gpt-3.5-turbo

    words related to chaos or disorder

    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
     sponsors
    -0.69
     sponsor
    -0.64
     treatment
    -0.60
    wait
    -0.58
    resources
    -0.57
     color
    -0.57
     sponsorship
    -0.56
     provider
    -0.55
     commercials
    -0.55
     author
    -0.55
    POSITIVE LOGITS
    anged
    4.21
    anging
    2.73
    anges
    1.76
    ange
    1.58
    angs
    1.52
    ANGE
    1.48
    angers
    1.39
    ANG
    1.38
    ang
    1.37
    anger
    1.34
    Activations Density 0.007%

    No Known Activations