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

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 3394
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific brand or company named "SM"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific acronym or shorthand related to a topic, likely "SM" referring to a particular theme or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icular
    -0.69
     Frie
    -0.68
     Lyme
    -0.68
     Authorization
    -0.67
    ãĥĥãĥĪ
    -0.65
     Ved
    -0.65
    ktop
    -0.65
    reon
    -0.64
    arium
    -0.64
    marked
    -0.64
    POSITIVE LOGITS
    ITH
    1.22
    ART
    1.12
    ASH
    0.97
    iley
    0.96
    ooth
    0.93
    ALL
    0.90
    ugg
    0.88
    ORPG
    0.85
    Gs
    0.84
    VD
    0.82
    Activations Density 0.015%

    No Known Activations