Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 22195
    Prev
    Next
    INDEX
    Explanations

    phrases related to negative events or statements

    oai_token-act-pair · gpt-3.5-turbo

    negative sentiment or expressions indicating issues or problems

    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
     preference
    -0.70
    opher
    -0.65
     maid
    -0.65
    åŃIJ
    -0.65
    oshop
    -0.64
    umbers
    -0.63
     proportion
    -0.63
     sore
    -0.63
    heet
    -0.63
    ·
    -0.62
    POSITIVE LOGITS
    _-
    1.59
    webkit
    0.95
    =-=-=-=-
    0.86
    âĢ¢âĢ¢
    0.85
    /-
    0.84
    =-=-=-=-=-=-=-=-
    0.81
    âĸº
    0.75
    something
    0.75
    including
    0.74
     AMA
    0.71
    Activations Density 0.062%

    No Known Activations