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. 4-RES-JB
    6. 5306
    Prev
    Next
    INDEX
    Explanations

    food-related phrases, particularly ones related to ingredients or food preparation techniques

    oai_token-act-pair · gpt-3.5-turbo

    past participles of verbs and their variations

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

    No Comments

    Negative Logits
    alter
    -0.76
    osponsors
    -0.69
    adra
    -0.66
    ãĥ¯ãĥ³
    -0.62
    involved
    -0.62
    ships
    -0.62
    issues
    -0.61
    BIT
    -0.61
    achu
    -0.61
    Reward
    -0.61
    POSITIVE LOGITS
    river
    1.07
    rive
    0.99
    own
    0.90
    irect
    0.88
    escription
    0.88
    eals
    0.83
    adoes
    0.83
    irection
    0.77
    igger
    0.76
    imentary
    0.76
    Activations Density 0.146%

    No Known Activations