© 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. 14853
    Prev
    Next
    INDEX
    Explanations

    mentions of physical attacks or confrontations

    oai_token-act-pair · gpt-3.5-turbo

    references to opponents or adversarial situations

    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
    obyl
    -0.65
    chwitz
    -0.62
    Minecraft
    -0.59
    ratom
    -0.59
     ______
    -0.57
    whatever
    -0.55
    tackle
    -0.54
    surv
    -0.53
     resil
    -0.53
     Pwr
    -0.52
    POSITIVE LOGITS
     authorities
    0.69
     spokeswoman
    0.67
     spokesman
    0.67
     latter
    0.67
     administrators
    0.65
     respondents
    0.65
     managers
    0.64
     spokesperson
    0.63
     officials
    0.61
     supervisors
    0.61
    Activations Density 0.997%

    No Known Activations