© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 6007
    Prev
    Next
    INDEX
    Explanations

    RNA-related terms and processes

    oai_token-act-pair · gpt-3.5-turbo

    references to RNA and related molecular biology concepts

    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
    ãĥī
    -0.75
    rament
    -0.74
    utory
    -0.72
     Papua
    -0.71
    Bron
    -0.71
     Ducks
    -0.71
     Gaul
    -0.66
     Newport
    -0.65
    owered
    -0.64
     largeDownload
    -0.64
    POSITIVE LOGITS
     molecule
    0.98
    seq
    0.98
     molecules
    0.97
    RNA
    0.84
    iotic
    0.84
     RNA
    0.83
    iotics
    0.83
     interference
    0.81
     replication
    0.81
    iot
    0.79
    Activations Density 0.009%

    No Known Activations