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. 962
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific names or locations containing the word "Way"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Way" in various contexts, often related to specific subjects or themes

    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
     sugg
    -0.84
    uster
    -0.84
    è¦ļéĨĴ
    -0.77
     prosec
    -0.77
    encer
    -0.76
    ĸļ
    -0.75
    ined
    -0.71
     repr
    -0.70
     mathemat
    -0.70
     quo
    -0.69
    POSITIVE LOGITS
    fare
    1.34
    ward
    1.27
    bill
    1.09
    WARD
    1.07
    way
    1.06
    finding
    1.00
    Way
    0.99
    PASS
    0.95
    Forward
    0.93
    point
    0.92
    Activations Density 0.015%

    No Known Activations