© 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. 2-RES-JB
    11. 9326
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical experiments and treatments

    oai_token-act-pair · gpt-3.5-turbo

    references to placebos and their effects in experimental contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eways
    -0.73
    hani
    -0.72
    laws
    -0.71
    lar
    -0.69
    Allen
    -0.68
     IPM
    -0.68
    clud
    -0.68
    Greg
    -0.67
    sections
    -0.67
    dar
    -0.66
    POSITIVE LOGITS
     placebo
    1.12
    veyard
    0.90
     analges
    0.70
     aspirin
    0.70
     Downs
    0.68
     mosqu
    0.67
     baseline
    0.67
     conclud
    0.66
     augment
    0.65
    ength
    0.65
    Activations Density 0.010%

    No Known Activations