© 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. 8-RES-JB
    11. 18557
    Prev
    Next
    INDEX
    Explanations

    phrases related to deception or betrayal

    oai_token-act-pair · gpt-3.5-turbo

    prepositions indicating relationships and actions

    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
     Clicker
    -0.71
    letters
    -0.71
    vice
    -0.67
    Zip
    -0.61
    natureconservancy
    -0.58
     Decay
    -0.57
    Untitled
    -0.56
    liction
    -0.55
    cot
    -0.55
    xes
    -0.55
    POSITIVE LOGITS
     by
    1.42
    by
    1.06
     BY
    1.04
     By
    0.84
     aback
    0.84
    upon
    0.80
    pez
    0.78
    bys
    0.77
    By
    0.76
    monton
    0.75
    Activations Density 0.214%

    No Known Activations