© 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. 3-RES-JB
    11. 23065
    Prev
    Next
    INDEX
    Explanations

    dates in the format "Dec [day]"

    oai_token-act-pair · gpt-3.5-turbo

    dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.87
    aird
    -0.79
    finder
    -0.68
     Archdemon
    -0.67
     priv
    -0.66
    culosis
    -0.64
    wegian
    -0.61
     Starr
    -0.61
    wered
    -0.60
     juggling
    -0.60
    POSITIVE LOGITS
    rypted
    1.13
    rypt
    1.11
    EMBER
    1.05
    enture
    1.03
    isions
    1.02
    oded
    1.01
    ryption
    1.00
    ibel
    0.98
    oder
    0.92
    oding
    0.88
    Activations Density 0.008%

    No Known Activations