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. 18537
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "middle"

    oai_token-act-pair · gpt-3.5-turbo

    references to "the middle" in various contexts

    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
    cci
    -0.73
    orthy
    -0.72
    osponsors
    -0.71
    edIn
    -0.69
    illard
    -0.68
    ilings
    -0.68
    vec
    -0.67
    OUP
    -0.67
    utical
    -0.65
    atche
    -0.65
    POSITIVE LOGITS
    stad
    0.83
     layer
    0.69
    middle
    0.67
     lan
    0.67
    woods
    0.66
    piece
    0.66
    west
    0.65
     lane
    0.65
     middle
    0.63
    western
    0.63
    Activations Density 0.011%

    No Known Activations