© 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. 8-RES-JB
    6. 22690
    Prev
    Next
    INDEX
    Explanations

    expressions related to body parts and actions associated with them

    oai_token-act-pair · gpt-3.5-turbo

    references to shaking or nodding heads, indicating disbelief or agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ipl
    -0.70
     Tycoon
    -0.68
     Vehicle
    -0.63
     Princ
    -0.62
    ngth
    -0.60
    Þ
    -0.60
    nor
    -0.59
    phis
    -0.59
     ASC
    -0.59
    illac
    -0.59
    POSITIVE LOGITS
     beads
    0.80
     politely
    0.79
     uncontroll
    0.77
     loudly
    0.77
     violently
    0.76
     vigorously
    0.75
     aloud
    0.74
     respectfully
    0.74
     disappro
    0.74
     invol
    0.74
    Activations Density 0.084%

    No Known Activations