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. 8734
    Prev
    Next
    INDEX
    Explanations

    instances of actions or characteristics tied to a group of people

    oai_token-act-pair · gpt-3.5-turbo

    the verb "are" and its forms used 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
    pedia
    -0.63
     Which
    -0.61
     Rout
    -0.60
    ricks
    -0.60
    ffe
    -0.60
    ooters
    -0.59
    ¨
    -0.59
    ization
    -0.58
     apology
    -0.57
     Solution
    -0.56
    POSITIVE LOGITS
    wolves
    0.91
     supposed
    0.78
    nt
    0.77
    tein
    0.73
    held
    0.68
    wolf
    0.68
     supposedly
    0.68
     married
    0.68
     subscribed
    0.67
     behold
    0.67
    Activations Density 0.201%

    No Known Activations