© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6977
    Prev
    Next
    INDEX
    Explanations

    phrases related to features or attributes

    oai_token-act-pair · gpt-3.5-turbo

    statements indicating significance, intensity, or emphasis in various contexts

    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
    irez
    -0.71
     vouchers
    -0.68
    anton
    -0.61
    usalem
    -0.59
     mismatch
    -0.58
    acion
    -0.56
     seminars
    -0.56
     Club
    -0.56
     Koran
    -0.55
    azing
    -0.55
    POSITIVE LOGITS
    \\\\\\\\
    0.70
    Els
    0.66
    ovie
    0.65
    ãĤ¢ãĥ«
    0.64
    Synopsis
    0.62
    ploy
    0.61
    SpaceEngineers
    0.60
    ãĤ®
    0.60
    \":
    0.59
     conce
    0.59
    Activations Density 1.997%

    No Known Activations