Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 10246
    Prev
    Next
    INDEX
    Explanations

    the word "whatever" in phrases

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "whatever" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enburg
    -0.92
    enberg
    -0.90
    ea
    -0.87
    iard
    -0.85
    por
    -0.81
    end
    -0.80
    ert
    -0.77
    enthal
    -0.75
    ades
    -0.73
    lic
    -0.72
    POSITIVE LOGITS
     else
    1.12
    soever
    1.12
     happened
    0.95
     happens
    0.93
     floats
    0.91
     semblance
    0.87
     sorts
    0.86
     transpired
    0.83
     kinds
    0.83
    THING
    0.81
    Activations Density 0.013%

    No Known Activations