© 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. 6-RES-JB
    11. 3734
    Prev
    Next
    INDEX
    Explanations

    phrases related to leaving or walking away

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "walk away."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chin
    -0.71
    achev
    -0.70
    ammy
    -0.70
    geries
    -0.70
    GY
    -0.67
    umn
    -0.67
    cluding
    -0.67
    alion
    -0.67
    xtap
    -0.66
    vironments
    -0.66
    POSITIVE LOGITS
     peacefully
    0.79
    ADRA
    0.74
     safely
    0.73
    RAG
    0.69
     AW
    0.64
     happily
    0.64
    ARC
    0.63
     Jagu
    0.63
    ALSE
    0.62
     victorious
    0.62
    Activations Density 0.024%

    No Known Activations