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. 11-RES-JB
    6. 3425
    Prev
    Next
    INDEX
    Explanations

    combinations of words with "and" connecting them

    oai_token-act-pair · gpt-3.5-turbo

    the word "and" or similar conjunctions that suggest connections between ideas or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    meet
    -0.71
    mount
    -0.66
    union
    -0.65
    umph
    -0.62
    ince
    -0.62
     Coming
    -0.61
    arry
    -0.61
    track
    -0.60
    rise
    -0.60
    existence
    -0.60
    POSITIVE LOGITS
     waited
    1.48
     gave
    1.46
     proceeded
    1.44
     threw
    1.38
     ensured
    1.36
     drove
    1.35
     undertook
    1.33
     took
    1.32
     apologized
    1.32
     blew
    1.32
    Activations Density 0.345%

    No Known Activations