© 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. 4-RES-JB
    11. 9392
    Prev
    Next
    INDEX
    Explanations

    ACGT nucleotide sequences in DNA or RNA sequences

    oai_token-act-pair · gpt-3.5-turbo

    references to genetic and biochemical elements related to health and disease

    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
    ãĥ¼ãĥĨãĤ£
    -0.81
     Tradable
    -0.81
    advertising
    -0.81
    ãĥĩãĤ£
    -0.77
    ãĥĥ
    -0.77
    Privacy
    -0.77
    Jimmy
    -0.76
    lehem
    -0.75
    éĹĺ
    -0.75
    sung
    -0.74
    POSITIVE LOGITS
     β
    1.08
     concentrations
    1.04
     phenotype
    1.01
     proteins
    1.01
    β
    1.00
     genes
    1.00
     substrate
    1.00
     toxicity
    0.99
     endogenous
    0.98
     induced
    0.97
    Activations Density 0.228%

    No Known Activations