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. 5698
    Prev
    Next
    INDEX
    Explanations

    mentions of the organization "PRI" or specific abbreviations related to it

    oai_token-act-pair · gpt-3.5-turbo

    the first-person singular pronoun "I" used repeatedly

    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
     balance
    -0.61
    imentary
    -0.61
     Cue
    -0.61
    ansas
    -0.61
    lined
    -0.60
    rules
    -0.59
     transports
    -0.59
     substitutes
    -0.59
    halla
    -0.58
    ynamic
    -0.58
    POSITIVE LOGITS
    AMI
    1.05
    HS
    0.96
    KE
    0.96
    BA
    0.96
    OUS
    0.94
    HL
    0.92
    BILITY
    0.92
    verson
    0.91
    'm
    0.90
    ALLY
    0.90
    Activations Density 0.053%

    No Known Activations