© 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. 12321
    Prev
    Next
    INDEX
    Explanations

    comparative terms and descriptions of size or quantity

    oai_token-act-pair · gpt-3.5-turbo

    terms related to measurements or quantities

    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
    ERSON
    -0.62
    igl
    -0.59
    errilla
    -0.58
     Borough
    -0.55
    _-_
    -0.55
    Engineers
    -0.54
    ffiti
    -0.54
    çĶ°
    -0.53
    qt
    -0.53
    uay
    -0.53
    POSITIVE LOGITS
     allowable
    0.72
    ebted
    0.65
     nodd
    0.64
     status
    0.63
    ucing
    0.60
     substrate
    0.60
     axis
    0.60
     permissible
    0.58
     particles
    0.58
     payoff
    0.57
    Activations Density 1.107%

    No Known Activations