© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 15065
    Prev
    Next
    INDEX
    Explanations

    times written in the format of hour:min p.m., especially focusing on the hour

    oai_token-act-pair · gpt-3.5-turbo

    repeated occurrences of the letter 'p'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Elven
    -0.70
     Shining
    -0.69
     Monarch
    -0.69
     Realms
    -0.67
     minded
    -0.67
    ãĤ¼ãĤ¦ãĤ¹
    -0.66
    æ©Ł
    -0.66
     Bohem
    -0.64
     Masters
    -0.64
    Cub
    -0.64
    POSITIVE LOGITS
    orters
    1.00
    ierce
    0.96
    orter
    0.96
    airs
    0.96
    uffed
    0.95
    isode
    0.94
    ylon
    0.91
    au
    0.90
    iers
    0.89
    atern
    0.89
    Activations Density 0.026%

    No Known Activations