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

    Neuronpedia

    APICircuit 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. 8-RES-JB
    6. 19854
    Prev
    Next
    INDEX
    Explanations

    future-oriented verbs related to predictions or expectations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to predictions and expectations

    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
    ude
    -0.77
    bard
    -0.74
     Dude
    -0.74
    cue
    -0.73
    clamation
    -0.68
    alien
    -0.68
    assault
    -0.67
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.66
    eatured
    -0.66
     trope
    -0.66
    POSITIVE LOGITS
     future
    0.87
     delays
    0.77
     successors
    0.76
     imminent
    0.75
     grandchildren
    0.72
     attendance
    0.70
     slowing
    0.69
     fewer
    0.68
     layoffs
    0.67
     delaying
    0.67
    Activations Density 0.122%

    No Known Activations