© 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. 11-RES-JB
    11. 21253
    Prev
    Next
    INDEX
    Explanations

    positive assessments of physical or mental health

    oai_token-act-pair · gpt-3.5-turbo

    terms related to physical condition and well-being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾
    -0.70
    ihad
    -0.69
     sacrific
    -0.68
    ãĤ¦ãĤ¹
    -0.68
    icides
    -0.68
    GBT
    -0.67
    ktop
    -0.66
    uces
    -0.65
    jri
    -0.64
     ãĤµ
    -0.64
    POSITIVE LOGITS
     shape
    1.25
     condition
    1.13
     spirits
    0.97
     position
    0.95
    shape
    0.93
     mood
    0.91
     stead
    0.88
     predicament
    0.85
     hands
    0.84
     financial
    0.83
    Activations Density 0.075%

    No Known Activations