© 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. 17093
    Prev
    Next
    INDEX
    Explanations

    numerical ratings given to various entities or products

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to ratings or evaluations

    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
    vous
    -0.91
    ansson
    -0.81
     Nou
    -0.80
    alter
    -0.78
     Alz
    -0.77
    prus
    -0.76
    adra
    -0.75
    adr
    -0.72
    phys
    -0.70
    apo
    -0.69
    POSITIVE LOGITS
     rated
    1.27
     veter
    1.04
     rating
    1.00
     ratings
    0.99
     Ratings
    0.96
     Rated
    0.90
    Rating
    0.90
    Rated
    0.86
    rating
    0.83
    Reviewed
    0.80
    Activations Density 0.010%

    No Known Activations