© 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. 8-RES-JB
    11. 1365
    Prev
    Next
    INDEX
    Explanations

    assertions or claims about various situations or conditions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating belief or claims about individuals or entities

    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
    Sorry
    -0.78
    course
    -0.71
    spect
    -0.71
    leaf
    -0.71
    reality
    -0.68
    hibition
    -0.68
    cell
    -0.67
    Reviewer
    -0.66
    Variable
    -0.64
    quickShipAvailable
    -0.64
    POSITIVE LOGITS
     originated
    0.81
     originate
    0.79
     envis
    0.69
     annex
    0.69
     have
    0.68
     spurred
    0.67
     lia
    0.67
     frequ
    0.67
     derive
    0.66
     accomp
    0.66
    Activations Density 0.106%

    No Known Activations