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. 11-RES-JB
    6. 7407
    Prev
    Next
    INDEX
    Explanations

    transition phrases indicating a preference or alternative

    oai_token-act-pair · gpt-3.5-turbo

    the word "rather" in various contexts

    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
    mberg
    -0.90
    }}}
    -0.67
    arent
    -0.65
    reen
    -0.64
    usha
    -0.63
    ayne
    -0.61
    amba
    -0.61
    kernel
    -0.60
    esville
    -0.60
    esian
    -0.59
    POSITIVE LOGITS
     than
    1.64
    than
    1.32
     Than
    1.13
     pathetic
    0.83
     omin
    0.82
     ironically
    0.82
     awkwardly
    0.81
     irritating
    0.80
     amusing
    0.79
     tame
    0.76
    Activations Density 0.025%

    No Known Activations