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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9-RES-JB
    6. 14637
    Prev
    Next
    INDEX
    Explanations

    adjectives or verbs related to a decrease in speed or activity

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of slowing down

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĦ
    -0.80
    çīĪ
    -0.76
    ãĥı
    -0.71
    arov
    -0.70
    alde
    -0.68
    ija
    -0.66
    alls
    -0.66
    ãĤ±
    -0.64
    istle
    -0.64
    irable
    -0.63
    POSITIVE LOGITS
    downs
    1.14
     down
    1.05
    down
    0.99
     pace
    0.95
     digestion
    0.91
     speeds
    0.91
     metabolism
    0.87
    DOWN
    0.84
     pacing
    0.83
     cooker
    0.82
    Activations Density 0.055%

    No Known Activations