© 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. 17081
    Prev
    Next
    INDEX
    Explanations

    references to continuity or persistence

    oai_token-act-pair · gpt-3.5-turbo

    emphatic expressions related to consistency and reliability

    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
    ahime
    -0.81
    rig
    -0.74
     DAC
    -0.73
    IDA
    -0.72
    lations
    -0.71
    SG
    -0.70
    DF
    -0.69
    LAN
    -0.69
     Tags
    -0.69
    iants
    -0.68
    POSITIVE LOGITS
    entimes
    0.90
    theless
    0.88
     dreamed
    0.81
     appreciated
    0.77
     strive
    0.75
     evolving
    0.75
     overlooked
    0.74
     thereafter
    0.73
     fascinated
    0.71
     assumed
    0.71
    Activations Density 0.029%

    No Known Activations