© 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. 8-RES-JB
    11. 17250
    Prev
    Next
    INDEX
    Explanations

    ratings and reviews

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to numerical ratings or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adr
    -0.96
     Alz
    -0.82
    ansson
    -0.76
    ĸļ
    -0.75
    ilus
    -0.74
    stasy
    -0.69
     Granger
    -0.67
    icz
    -0.67
    orial
    -0.65
    ERY
    -0.65
    POSITIVE LOGITS
     ratings
    1.12
     rating
    1.11
     Ratings
    0.97
    Rating
    0.92
    Reviewer
    0.89
     Rating
    0.88
     downgrade
    0.88
    âĺħâĺħ
    0.88
     rated
    0.83
    rating
    0.83
    Activations Density 0.042%

    No Known Activations