© 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. 12363
    Prev
    Next
    INDEX
    Explanations

    words related to providing help or support to others

    oai_token-act-pair · gpt-3.5-turbo

    references to assistance or support in various contexts

    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
    place
    -0.76
    nu
    -0.74
    Pict
    -0.72
    bur
    -0.69
    peror
    -0.66
    bish
    -0.66
    ×IJ
    -0.64
    é¾
    -0.63
    meat
    -0.62
     vow
    -0.62
    POSITIVE LOGITS
     assist
    0.98
     assisting
    0.95
     aids
    0.94
     assists
    0.86
     aid
    0.78
     assistance
    0.78
     Assist
    0.78
     assisted
    0.77
    assisted
    0.77
    ments
    0.74
    Activations Density 0.022%

    No Known Activations