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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 21299
    Prev
    Next
    INDEX
    Explanations

    prefixes followed by a hyphen and a word, potentially related to negative or problematic situations

    oai_token-act-pair · gpt-3.5-turbo

    negative connotations or outcomes associated with actions

    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
     Burr
    -0.79
     Confederation
    -0.79
     Norris
    -0.66
     revised
    -0.64
     clenched
    -0.64
     Chambers
    -0.63
     cir
    -0.63
     Harrington
    -0.63
     Debor
    -0.62
     Nicarag
    -0.62
    POSITIVE LOGITS
    based
    1.29
    advertising
    1.16
    to
    1.15
    level
    1.12
    through
    1.11
    sized
    1.11
    related
    1.10
    style
    1.06
    type
    1.05
    tun
    1.04
    Activations Density 0.181%

    No Known Activations