© 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. 4-RES-JB
    11. 10219
    Prev
    Next
    INDEX
    Explanations

    hyphenated words with a prefix 're-' indicating repetition or restoration

    oai_token-act-pair · gpt-3.5-turbo

    words related to re-elections and related political contexts

    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
    ulhu
    -1.08
     Dickinson
    -0.72
     Nah
    -0.69
     DeV
    -0.66
     Williamson
    -0.66
    åŃ
    -0.66
     Slim
    -0.66
     reviewers
    -0.65
     Achievements
    -0.65
     Loll
    -0.63
    POSITIVE LOGITS
    edition
    1.14
    position
    1.06
    talk
    1.04
    issue
    1.03
    introdu
    1.02
    elected
    1.01
    tool
    1.00
    emphasis
    0.99
    balance
    0.99
    signed
    0.98
    Activations Density 0.053%

    No Known Activations