© 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. 8-RES-JB
    11. 22509
    Prev
    Next
    INDEX
    Explanations

    instances where the speaker expresses their personal thoughts or opinions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "that."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aukee
    -0.82
    ãĥīãĥ©
    -0.79
    aunder
    -0.78
    ciples
    -0.76
    iped
    -0.74
    ãĥ©ãĥ³
    -0.68
    IELD
    -0.68
    earable
    -0.67
    ipers
    -0.67
    cakes
    -0.67
    POSITIVE LOGITS
     although
    0.82
     contradicts
    0.81
     happens
    0.77
     applies
    0.75
     translates
    0.75
     happened
    0.73
     justifies
    0.73
     relates
    0.73
     sounds
    0.72
     whoever
    0.70
    Activations Density 0.247%

    No Known Activations