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. 15904
    Prev
    Next
    INDEX
    Explanations

    terms related to the characteristics and actions of people or entities in various contexts, such as profession, societal roles, and traits

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to organizations, leadership, and social structures

    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
    autions
    -0.57
     recol
    -0.57
    osponsors
    -0.57
     doubts
    -0.57
     disclaim
    -0.56
     signatures
    -0.56
     rumors
    -0.56
     snowy
    -0.56
     glitches
    -0.55
     Mub
    -0.55
    POSITIVE LOGITS
    Reviewer
    0.73
     viz
    0.68
    href
    0.64
    ĸļ
    0.62
    estamp
    0.61
     namely
    0.60
    being
    0.60
     relating
    0.60
    votes
    0.59
    iership
    0.59
    Activations Density 1.242%

    No Known Activations