© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 17494
    Prev
    Next
    INDEX
    Explanations

    phrases related to the peer review process

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word 'reviewed' and related terms indicating the review process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vor
    -0.72
    kt
    -0.72
    adra
    -0.71
    kay
    -0.69
    bang
    -0.68
     Soldier
    -0.68
    tor
    -0.66
     Dome
    -0.65
    bs
    -0.65
    iliar
    -0.65
    POSITIVE LOGITS
    Reviewed
    1.09
     obser
    0.94
    igion
    0.89
    rarily
    0.81
    ometimes
    0.80
    agascar
    0.80
    umenthal
    0.80
    ouble
    0.79
    INTON
    0.78
    VIDIA
    0.77
    Activations Density 0.036%

    No Known Activations