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. 5-RES-JB
    6. 13506
    Prev
    Next
    INDEX
    Explanations

    words relating to spatial adjacency or proximity

    oai_token-act-pair · gpt-3.5-turbo

    terms related to spatial relationships and adjacency

    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
    fare
    -0.81
    GO
    -0.78
    uay
    -0.71
    tu
    -0.70
    boys
    -0.68
    odor
    -0.67
    zie
    -0.65
    ball
    -0.65
    rimp
    -0.64
    ocker
    -0.63
    POSITIVE LOGITS
     thereto
    0.87
     adjacent
    0.75
     adjoining
    0.70
    minster
    0.69
    itor
    0.69
    ãĥ¼ãĥĨ
    0.69
    ï¸
    0.68
     spaces
    0.68
    66666666
    0.68
    isode
    0.66
    Activations Density 0.011%

    No Known Activations