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. 4-RES-JB
    6. 22813
    Prev
    Next
    INDEX
    Explanations

    start sentences with the word "Having"

    oai_token-act-pair · gpt-3.5-turbo

    the word "Having" and its variations, indicating a focus on possession or states of being

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

    No Comments

    Negative Logits
    etter
    -0.66
    ocol
    -0.65
     Echo
    -0.64
     Slovakia
    -0.61
     Dispatch
    -0.61
     Pipeline
    -0.58
    VR
    -0.56
     Explosion
    -0.56
     caption
    -0.55
     Regions
    -0.55
    POSITIVE LOGITS
     undergone
    1.05
     been
    1.03
     gotten
    0.87
     eaten
    0.86
     done
    0.84
     listened
    0.82
     seen
    0.80
     heard
    0.78
    been
    0.76
     begun
    0.75
    Activations Density 0.030%

    No Known Activations