© 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. 9-RES-JB
    11. 1797
    Prev
    Next
    INDEX
    Explanations

    contractions where the word "don't" appears

    oai_token-act-pair · gpt-3.5-turbo

    negative assertions or denials

    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
     pione
    -0.71
    ò
    -0.68
    emetery
    -0.65
    ñ
    -0.64
     subur
    -0.64
     teasp
    -0.64
    redients
    -0.62
    ersed
    -0.61
    edient
    -0.61
    ailability
    -0.59
    POSITIVE LOGITS
     condone
    1.14
     hesitate
    1.10
     know
    1.07
     intend
    1.06
     necessarily
    1.06
     mean
    1.05
     wanna
    1.05
     believe
    1.05
     think
    1.04
     recommend
    0.95
    Activations Density 0.074%

    No Known Activations