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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 6-RES-JB
    6. 10220
    Prev
    Next
    INDEX
    Explanations

    emoji sequences often representing emotions or reactions

    oai_token-act-pair · gpt-3.5-turbo

    special characters and symbols, particularly those commonly used in social media contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Manit
    -0.70
     Gillespie
    -0.70
     Abyssal
    -0.68
     Sakuya
    -0.67
     Sidd
    -0.67
     Takeru
    -0.66
    wagen
    -0.65
     Reloaded
    -0.64
     Bain
    -0.64
     recorder
    -0.63
    POSITIVE LOGITS
    ¥ŀ
    1.29
    Ĵ
    1.28
    Ķ
    1.25
    ĵ
    1.24
    Į
    1.21
    ĻĤ
    1.18
    į
    1.18
    ĵĺ
    1.16
    İ
    1.15
    ķ
    1.08
    Activations Density 0.007%

    No Known Activations