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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9818
    Prev
    Next
    INDEX
    Explanations

    words ending in 'ing'

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and present participles, which are verbs ending in 'ing'

    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
     uncond
    -0.63
    ACP
    -0.63
     Columb
    -0.63
    ãĥŀ
    -0.61
     COURT
    -0.61
     actionGroup
    -0.59
    å£
    -0.57
    ignty
    -0.55
    ãĥ¤
    -0.54
     recoil
    -0.53
    POSITIVE LOGITS
    redients
    1.36
    tons
    1.25
    lass
    1.20
    roup
    1.06
    hetti
    1.05
    bats
    1.03
    lasses
    1.00
    hoff
    0.99
    uez
    0.96
    ham
    0.94
    Activations Density 0.066%

    No Known Activations