© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 15695
    Prev
    Next
    INDEX
    Explanations

    terms related to interactions or connections between different elements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to interaction or relationships between entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     blindly
    -0.62
     bribes
    -0.60
     refuge
    -0.59
     proofs
    -0.58
     fools
    -0.58
     payday
    -0.58
     exerc
    -0.57
     bruises
    -0.57
     peanuts
    -0.57
     Examiner
    -0.57
    POSITIVE LOGITS
    disciplinary
    1.42
    stitial
    1.39
    locking
    1.34
    racial
    1.34
    continental
    1.34
    dimensional
    1.31
    species
    1.28
    lude
    1.23
    iors
    1.22
    connect
    1.21
    Activations Density 0.015%

    No Known Activations