Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 0-RES-JB
    6. 3196
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific locations or entities named "Cross"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Cross" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sov
    -0.67
     asleep
    -0.67
    Downloadha
    -0.63
     lav
    -0.63
     aspiration
    -0.61
    */(
    -0.61
    sylv
    -0.60
     occupant
    -0.59
    temp
    -0.59
    vana
    -0.59
    POSITIVE LOGITS
     Cross
    3.98
    Cross
    2.83
    cross
    2.34
     cross
    2.28
     Crescent
    1.53
     crosses
    1.51
     Crossing
    1.47
     crossed
    1.23
     Cros
    1.10
     crossing
    1.06
    Activations Density 0.015%

    No Known Activations