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. 193
    Prev
    Next
    INDEX
    Explanations

    technical details and specifications related to mechanical or electronic devices

    oai_token-act-pair · gpt-3.5-turbo

    components and mechanisms related to mechanical systems and assembly

    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
    Politics
    -0.86
     Venezuel
    -0.84
    oké
    -0.76
     Niet
    -0.73
     Transgender
    -0.73
     transgender
    -0.72
     Brave
    -0.71
     Criminal
    -0.71
     flashbacks
    -0.70
     LGBT
    -0.70
    POSITIVE LOGITS
     protr
    1.18
     removable
    1.17
     diameter
    1.11
     adjustable
    1.10
     angled
    1.01
     fitted
    1.01
     srfAttach
    0.99
     connector
    0.96
    iameter
    0.95
     cylinder
    0.94
    Activations Density 0.726%

    No Known Activations