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. 2-RES-JB
    6. 9926
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to dealing with challenges or difficult situations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to coping with various challenges or adversities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ended
    -0.73
    roma
    -0.71
    lav
    -0.68
    rust
    -0.68
    enic
    -0.68
    eneg
    -0.68
    hem
    -0.67
    reme
    -0.67
    stab
    -0.65
    cius
    -0.65
    POSITIVE LOGITS
     cope
    0.86
    acebook
    0.79
     arrang
    0.77
     survives
    0.75
     horizont
    0.74
    estyles
    0.72
    atives
    0.71
    ITION
    0.71
    izers
    0.70
     coping
    0.70
    Activations Density 0.007%

    No Known Activations