© 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. 4-RES-JB
    11. 7355
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Beh" followed by various suffixes or prefixes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Beh" and its variations, likely indicating a focus on behavior-related terms or discussions

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

    No Comments

    Negative Logits
     bunk
    -0.67
    enthal
    -0.67
    intendent
    -0.67
     Sapp
    -0.65
    eous
    -0.64
     Roof
    -0.64
    ismo
    -0.64
    BOX
    -0.64
     Kaepernick
    -0.63
    ç¥ŀ
    -0.62
    POSITIVE LOGITS
    aviour
    1.50
    avior
    1.03
     Beh
    1.02
    abus
    1.02
    beh
    0.99
    avin
    0.83
    av
    0.83
    uate
    0.83
    aving
    0.83
    reath
    0.82
    Activations Density 0.006%

    No Known Activations