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. 18059
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names that end with the letters "off"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of being "off" or not active

    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
    ãĤ©
    -0.82
    aceous
    -0.74
    ãĤ§
    -0.70
    CVE
    -0.66
    76561
    -0.66
    ãĤ£
    -0.64
    SHARE
    -0.64
    ãĥ£
    -0.63
    umbing
    -0.62
    entary
    -0.62
    POSITIVE LOGITS
    ices
    1.07
    ense
    1.00
    erence
    0.87
    ENSE
    0.85
    rey
    0.84
    enses
    0.83
    sets
    0.82
    ments
    0.82
    ishly
    0.82
    enders
    0.81
    Activations Density 0.015%

    No Known Activations