© 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. 7974
    Prev
    Next
    INDEX
    Explanations

    phrases related to impactful actions or events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to competition and outcomes

    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
     abundantly
    -0.75
    utenberg
    -0.71
     foremost
    -0.68
     centrally
    -0.60
     merit
    -0.59
     nutshell
    -0.57
     prominently
    -0.55
     hereby
    -0.55
     adip
    -0.55
     seamlessly
    -0.54
    POSITIVE LOGITS
    ings
    1.84
    ments
    1.68
    ment
    1.46
    ing
    1.45
    ership
    1.31
    ations
    1.31
    ement
    1.23
    ements
    1.23
    ions
    1.23
    INGS
    1.21
    Activations Density 0.339%

    No Known Activations