© 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. 6-RES-JB
    11. 1705
    Prev
    Next
    INDEX
    Explanations

    percentages related to increases and decreases in various statistics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to statistical increases and decreases in data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     staples
    -0.64
    GES
    -0.58
    ALE
    -0.58
    PAR
    -0.55
     Monstrous
    -0.55
     muster
    -0.54
     Cabin
    -0.54
     Parables
    -0.54
    MET
    -0.54
     Purg
    -0.54
    POSITIVE LOGITS
    xual
    1.04
    over
    0.90
    onential
    0.82
    ulative
    0.78
     rate
    0.77
     subsequ
    0.76
    ivist
    0.75
    erence
    0.75
    itures
    0.75
    ait
    0.73
    Activations Density 0.095%

    No Known Activations