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. 2851
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Essar" followed by varying degrees of relevance-related words, or the word "Essentials"

    oai_token-act-pair · gpt-3.5-turbo

    the brand "Ess" and its associations 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
     sight
    -0.70
    è¦ļéĨĴ
    -0.68
    ategory
    -0.65
    btn
    -0.61
    ²¾
    -0.61
    faced
    -0.61
    =-=-=-=-=-=-=-=-
    -0.61
    ãĥ£
    -0.60
    Interested
    -0.59
    outine
    -0.59
    POSITIVE LOGITS
    entials
    1.58
    endon
    1.25
    ences
    1.24
    ential
    1.03
    ensible
    0.99
    entially
    0.97
    inite
    0.95
    aults
    0.91
    linger
    0.90
    gard
    0.90
    Activations Density 0.010%

    No Known Activations