© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 11991
    Prev
    Next
    INDEX
    Explanations

    present participle verbs ending in '-ing' that may have a negative connotation

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and their forms related to actions or ongoing states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IB
    -0.57
    Gate
    -0.57
    channelAvailability
    -0.55
    arter
    -0.55
     Cards
    -0.54
    href
    -0.54
     Sale
    -0.53
     Grayson
    -0.52
    acca
    -0.52
     Rowling
    -0.52
    POSITIVE LOGITS
    ateful
    0.70
    uated
    0.65
    idable
    0.63
    rences
    0.62
    arious
    0.61
    igious
    0.59
    uates
    0.59
    acious
    0.59
    entimes
    0.58
    theless
    0.58
    Activations Density 0.299%

    No Known Activations