© 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. 1-RES-JB
    11. 16433
    Prev
    Next
    INDEX
    Explanations

    words related to re-creating or redoing something, such as "remake" and "remix"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "remake" and its variations related to the concept of remaking or adapting existing works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Streamer
    -0.75
    bra
    -0.69
    Ku
    -0.68
    regulated
    -0.68
    Jr
    -0.63
    Bus
    -0.63
    externalActionCode
    -0.63
    Org
    -0.61
    Senior
    -0.61
    Discussion
    -0.61
    POSITIVE LOGITS
     remake
    1.21
    ngth
    0.96
     Reboot
    0.87
     reboot
    0.86
     psychiat
    0.74
    aliation
    0.73
     rewrite
    0.72
     XCOM
    0.68
     Reincarn
    0.68
    Maker
    0.67
    Activations Density 0.014%

    No Known Activations