© 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. 3-RES-JB
    11. 12645
    Prev
    Next
    INDEX
    Explanations

    terms related to acquisition, progress, or success

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "gained" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reckoned
    -0.65
    iso
    -0.63
    pled
    -0.60
    hov
    -0.59
    meta
    -0.58
     crying
    -0.57
    tes
    -0.57
    machine
    -0.57
     Patri
    -0.56
    hal
    -0.55
    POSITIVE LOGITS
    esville
    0.88
    icult
    0.84
    esses
    0.80
    itive
    0.80
     notoriety
    0.79
     traction
    0.76
    aroo
    0.76
    /+
    0.75
    eteenth
    0.74
     gained
    0.73
    Activations Density 0.015%

    No Known Activations