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. 0-RES-JB
    6. 11210
    Prev
    Next
    INDEX
    Explanations

    phrases related to adding something to an existing entity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "adds" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     democratically
    -0.69
     Question
    -0.61
     politic
    -0.60
     toilet
    -0.59
     face
    -0.59
     seizure
    -0.56
     peaceful
    -0.56
     malfunction
    -0.55
     Marxist
    -0.55
     vacant
    -0.55
    POSITIVE LOGITS
     adds
    3.36
    Adds
    2.23
     Adds
    2.22
     added
    1.87
     add
    1.74
     contributes
    1.65
     enhances
    1.62
     expands
    1.58
     introduces
    1.57
     removes
    1.52
    Activations Density 0.014%

    No Known Activations