© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 17263
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a requirement or condition

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the notion of being unable to accomplish something without certain conditions or elements present

    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
    ãĥī
    -0.79
    ery
    -0.77
    quer
    -0.75
    ãĥĺ
    -0.73
    mon
    -0.73
    late
    -0.72
    roller
    -0.71
     Rebell
    -0.71
    rolled
    -0.71
    estate
    -0.69
    POSITIVE LOGITS
     risking
    0.95
     encountering
    0.87
     sacrificing
    0.85
     knowing
    0.85
     recourse
    0.82
     compromising
    0.79
     mentioning
    0.77
     regard
    0.76
     submitting
    0.73
     obtaining
    0.73
    Activations Density 0.060%

    No Known Activations