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. 3-RES-JB
    6. 2345
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Fell" with various activation levels

    oai_token-act-pair · gpt-3.5-turbo

    the recurring mention of the term "fell" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eers
    -0.81
     scratch
    -0.65
    eer
    -0.61
     antioxid
    -0.61
     Blaz
    -0.60
    OTO
    -0.60
    RELATED
    -0.60
    LOC
    -0.58
    GO
    -0.58
    ALS
    -0.58
    POSITIVE LOGITS
    owship
    1.83
    fell
    1.18
    ows
    1.05
    acies
    1.02
    atio
    0.92
    borough
    0.89
    bage
    0.88
    mere
    0.85
    nesday
    0.84
    uchi
    0.82
    Activations Density 0.013%

    No Known Activations