© 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. 19651
    Prev
    Next
    INDEX
    Explanations

    words related to caution or measures being taken to prevent unwanted outcomes

    oai_token-act-pair · gpt-3.5-turbo

    words related to caution and preventive measures

    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
    igslist
    -0.82
    wagen
    -0.79
    yss
    -0.75
    idity
    -0.73
    ategory
    -0.72
    ufact
    -0.72
    ench
    -0.72
    hovah
    -0.67
    song
    -0.66
    kamp
    -0.65
    POSITIVE LOGITS
    ALLY
    0.93
    measures
    0.73
    andum
    0.72
     measures
    0.70
    aneously
    0.69
    LY
    0.69
     observation
    0.68
     caveat
    0.68
     arrang
    0.68
     advised
    0.67
    Activations Density 0.203%

    No Known Activations