© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 18200
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases starting with "due to"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "due to" indicating causal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ires
    -0.84
    soever
    -0.83
    aire
    -0.80
    bats
    -0.78
    lime
    -0.78
    lest
    -0.77
    cember
    -0.76
    anooga
    -0.76
    yssey
    -0.75
    iac
    -0.74
    POSITIVE LOGITS
     lack
    1.24
     sheer
    1.09
     complications
    1.07
     unforeseen
    1.05
     inexper
    1.04
     exhaustion
    1.02
     inconsistencies
    0.98
     insufficient
    0.96
     differences
    0.95
     inaction
    0.94
    Activations Density 0.090%

    No Known Activations