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. 20312
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "pattern"

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to a type of squash or pumpkins

    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
    ptive
    -0.69
    Bone
    -0.67
    fixes
    -0.64
    Stream
    -0.64
    ãĥ³ãĤ¸
    -0.64
     Amph
    -0.63
    Snake
    -0.61
    ãĥ
    -0.60
    ves
    -0.60
    URA
    -0.59
    POSITIVE LOGITS
    atural
    1.07
    estern
    1.02
    aturally
    0.96
    sburgh
    0.93
    ingen
    0.91
    orks
    0.83
    ature
    0.82
    orrow
    0.81
    orld
    0.81
    een
    0.80
    Activations Density 0.033%

    No Known Activations