© 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. 4-RES-JB
    11. 20518
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific entity or concept denoted by a series of alphanumeric characters followed by a hyphen

    oai_token-act-pair · gpt-3.5-turbo

    items or classifications associated with SCP (Secure, Contain, Protect) documentation

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

    No Comments

    Negative Logits
    ieri
    -0.74
     âĶľ
    -0.68
     Norris
    -0.67
    pec
    -0.66
     htt
    -0.66
     FML
    -0.65
     zip
    -0.65
     Pepsi
    -0.65
     Confederation
    -0.63
     pause
    -0.61
    POSITIVE LOGITS
    mediated
    1.08
    style
    1.03
    friendly
    1.00
    based
    1.00
    related
    0.99
    sama
    0.98
    driven
    0.98
    derived
    0.98
    type
    0.96
    themed
    0.95
    Activations Density 0.128%

    No Known Activations