© 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. 4-RES-JB
    11. 6658
    Prev
    Next
    INDEX
    Explanations

    technical terms or names containing special characters like symbols and numbers

    oai_token-act-pair · gpt-3.5-turbo

    numeric values or counts related to various topics

    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
     destro
    -0.85
    hement
    -0.82
     helicop
    -0.73
    bley
    -0.72
    ledged
    -0.67
     Jagu
    -0.65
     favoured
    -0.64
     disadvant
    -0.63
     abolish
    -0.62
     undermin
    -0.62
    POSITIVE LOGITS
     largeDownload
    0.73
    ALT
    0.71
    PRESS
    0.71
    SCP
    0.69
    ergy
    0.67
    ccording
    0.67
    Temperature
    0.67
    OVER
    0.66
    Volume
    0.66
    Overview
    0.64
    Activations Density 0.251%

    No Known Activations