© 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. 10-RES-JB
    11. 12371
    Prev
    Next
    INDEX
    Explanations

    verbs related to the ability to do or achieve something

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs indicating ability or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    listed
    -0.73
    DERR
    -0.72
     Likes
    -0.72
     Eating
    -0.72
     reflections
    -0.70
    checking
    -0.70
    laughter
    -0.69
     Slug
    -0.68
     Info
    -0.67
     photography
    -0.67
    POSITIVE LOGITS
     convince
    1.52
     persuade
    1.48
     overcome
    1.35
     afford
    1.33
     appease
    1.27
     prevail
    1.27
     justify
    1.26
     regain
    1.26
     cope
    1.24
     muster
    1.24
    Activations Density 0.223%

    No Known Activations