© 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. 11-RES-JB
    11. 2222
    Prev
    Next
    INDEX
    Explanations

    adjectives that compare different qualities

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that describe varying levels of intensity or quality related to topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulnerability
    -0.74
    AIR
    -0.70
    forestation
    -0.70
    ledge
    -0.68
    Cola
    -0.67
    CRE
    -0.65
    rogram
    -0.64
    CLE
    -0.64
    awareness
    -0.63
    successfully
    -0.63
    POSITIVE LOGITS
     parts
    1.36
     aspects
    1.34
     portions
    1.30
     versions
    1.26
     sections
    1.25
     ones
    1.24
     corners
    1.15
     facets
    1.12
     varieties
    1.10
     elements
    1.06
    Activations Density 0.221%

    No Known Activations