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. 3-RES-JB
    6. 18932
    Prev
    Next
    INDEX
    Explanations

    contractions of "have."

    oai_token-act-pair · gpt-3.5-turbo

    the contraction "I've," indicating first-person narrative or reflective statements

    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
    eem
    -0.63
    Reviewer
    -0.59
    ortmund
    -0.56
    imately
    -0.56
    izes
    -0.56
     separates
    -0.56
     manifests
    -0.55
     denotes
    -0.55
    iates
    -0.54
    ealing
    -0.54
    POSITIVE LOGITS
     been
    1.38
     gotta
    1.32
    been
    1.26
     Been
    1.21
     got
    1.15
     gotten
    1.11
     gone
    0.97
    hran
    0.90
    gotten
    0.88
     done
    0.86
    Activations Density 0.040%

    No Known Activations