© 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. 9-RES-JB
    11. 15356
    Prev
    Next
    INDEX
    Explanations

    mentions or references to the superhero character "Spider-Man"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the "Spider-Man" franchise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     interval
    -0.74
     miscar
    -0.69
     uncond
    -0.68
     interstate
    -0.68
     offence
    -0.68
     redress
    -0.67
    assetsadobe
    -0.66
     embargo
    -0.66
     disg
    -0.65
     stretch
    -0.65
    POSITIVE LOGITS
    Mania
    0.98
    vill
    0.98
    Woman
    0.97
    verse
    0.96
    Man
    0.95
    mania
    0.94
    Girl
    0.94
    Cola
    0.93
    talk
    0.91
    sama
    0.90
    Activations Density 0.062%

    No Known Activations