© 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. 6-RES-JB
    11. 17570
    Prev
    Next
    INDEX
    Explanations

    terms related to detailed analysis or investigation

    oai_token-act-pair · gpt-3.5-turbo

    references to examination or scrutiny of subjects

    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
    âĹ¼
    -0.80
    Torrent
    -0.69
    activate
    -0.67
    gren
    -0.65
    activated
    -0.65
    fires
    -0.65
    MER
    -0.64
    cell
    -0.63
    blue
    -0.62
     Hots
    -0.61
    POSITIVE LOGITS
    ively
    0.87
    ĸļ
    0.83
     Probe
    0.81
     microsc
    0.79
     examination
    0.77
    mble
    0.76
    alus
    0.76
     favorably
    0.74
    osterone
    0.74
    isites
    0.73
    Activations Density 0.037%

    No Known Activations