Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 17442
    Prev
    Next
    INDEX
    Explanations

    verbs related to ability or inability

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing inability or difficulty in achieving certain actions or goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ammo
    -0.63
    articles
    -0.61
     Actor
    -0.61
    origin
    -0.60
     Agents
    -0.60
     Tactics
    -0.60
     sprinkled
    -0.59
     Directions
    -0.59
    assault
    -0.59
    heavy
    -0.58
    POSITIVE LOGITS
     Pradesh
    0.79
    ioned
    0.79
     compe
    0.74
     afford
    0.73
     anymore
    0.72
    awaru
    0.69
    osaurus
    0.69
    bos
    0.68
    bodied
    0.68
    ometers
    0.67
    Activations Density 0.041%

    No Known Activations