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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 11124
    Prev
    Next
    INDEX
    Explanations

    phrases indicating prior knowledge, awareness, or possessions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating prior knowledge or experiences

    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
    Downloadha
    -0.72
     CST
    -0.67
    milo
    -0.66
    pmwiki
    -0.62
     Techniques
    -0.61
    luck
    -0.58
     Survive
    -0.58
     Sco
    -0.56
    amen
    -0.56
    kai
    -0.56
    POSITIVE LOGITS
    ledged
    0.68
    gebra
    0.67
    readable
    0.65
    vier
    0.65
     ABE
    0.64
    hire
    0.64
    izable
    0.63
    entials
    0.62
     proofs
    0.62
    incible
    0.61
    Activations Density 0.149%

    No Known Activations