© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 10757
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations or organizations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating location and presence of entities or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FILE
    -0.65
     concurrently
    -0.63
    coon
    -0.63
    oldown
    -0.63
     reperto
    -0.62
     whereas
    -0.62
     suspic
    -0.61
    */(
    -0.61
     favorably
    -0.60
    quez
    -0.60
    POSITIVE LOGITS
     ours
    0.94
     Patreon
    0.80
     Blog
    0.79
     HuffPost
    0.74
     Ao
    0.74
     Subtle
    0.72
     EW
    0.72
     LW
    0.71
     Pod
    0.71
     Bearing
    0.71
    Activations Density 0.086%

    No Known Activations