© 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. 2-RES-JB
    11. 24038
    Prev
    Next
    INDEX
    Explanations

    instances of emphasis or intensification within phrases

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "total" and its variations, indicating quantifiable amounts or sums

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lazarus
    -0.72
    lyn
    -0.69
    rir
    -0.66
     Carbuncle
    -0.65
     Dwell
    -0.65
     Cosponsors
    -0.65
    rium
    -0.65
    heid
    -0.64
    pires
    -0.64
    yer
    -0.64
    POSITIVE LOGITS
    itarian
    0.93
    GV
    0.74
    idad
    0.71
    ISM
    0.67
     totals
    0.67
     tally
    0.67
    iza
    0.67
    ism
    0.66
     Estimated
    0.65
     elimination
    0.64
    Activations Density 0.017%

    No Known Activations