© 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. 1-RES-JB
    11. 24159
    Prev
    Next
    INDEX
    Explanations

    specific dates in the format "MM/DD/YYYY"

    oai_token-act-pair · gpt-3.5-turbo

    dates formatted in a specific way (MM/DD/YYYY)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ierrez
    -0.71
    awaru
    -0.71
    espie
    -0.71
     Palestin
    -0.68
    ategic
    -0.67
    matic
    -0.65
    axy
    -0.65
    agues
    -0.65
    oles
    -0.65
    wagen
    -0.64
    POSITIVE LOGITS
     01
    1.35
     02
    1.28
     00
    1.21
     03
    1.19
     09
    1.16
     05
    1.12
     06
    1.11
     07
    1.09
     04
    1.06
     08
    1.04
    Activations Density 0.005%

    No Known Activations