© 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. 3-RES-JB
    6. 10663
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific measurements

    oai_token-act-pair · gpt-3.5-turbo

    references to measurements and their accuracy

    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
    redo
    -0.87
    ressive
    -0.80
    illard
    -0.78
    lins
    -0.77
    bara
    -0.75
    burning
    -0.73
    ita
    -0.73
    sle
    -0.69
    role
    -0.68
    cop
    -0.68
    POSITIVE LOGITS
     measurements
    1.14
     measurement
    1.02
    Measure
    0.96
     measuring
    0.93
     instruments
    0.91
     Measure
    0.86
     glim
    0.86
     mathemat
    0.85
     instrument
    0.84
     measure
    0.82
    Activations Density 0.017%

    No Known Activations