© 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. 21995
    Prev
    Next
    INDEX
    Explanations

    words related to remixing and versions thereof

    oai_token-act-pair · gpt-3.5-turbo

    terms related to remixes and remix culture

    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
    lehem
    -0.79
     Lumpur
    -0.72
    ttp
    -0.66
    ocaust
    -0.66
     Peninsula
    -0.66
    OTS
    -0.62
     Pul
    -0.62
    OTT
    -0.61
    ########
    -0.61
     Glob
    -0.60
    POSITIVE LOGITS
     remix
    1.06
    es
    1.04
    Mix
    0.85
     Remix
    0.81
    mble
    0.76
     Mix
    0.73
    eed
    0.73
    edIn
    0.72
    orial
    0.70
    icons
    0.70
    Activations Density 0.015%

    No Known Activations