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. 2-RES-JB
    6. 20202
    Prev
    Next
    INDEX
    Explanations

    verbs ending in 'ing' related to physical actions or visual experiences

    oai_token-act-pair · gpt-3.5-turbo

    the term "bing" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     breeze
    -0.66
    ribut
    -0.59
     understandable
    -0.58
    Reviewer
    -0.58
     scrimmage
    -0.57
    sub
    -0.56
     controlled
    -0.55
     unmarked
    -0.55
     simplest
    -0.54
    OURCE
    -0.53
    POSITIVE LOGITS
    bing
    1.25
    tons
    1.00
    ton
    0.91
    gdala
    0.87
    HAM
    0.87
    ham
    0.81
    redients
    0.81
    ling
    0.80
    lehem
    0.78
    pload
    0.76
    Activations Density 0.013%

    No Known Activations