© 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. 1-RES-JB
    11. 971
    Prev
    Next
    INDEX
    Explanations

    the word "hem" either as a standalone or as part of a larger term

    oai_token-act-pair · gpt-3.5-turbo

    terms related to hemoglobin and blood-related conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĺħâĺħ
    -0.79
    âĺħ
    -0.79
    ×Ķ
    -0.76
    ITAL
    -0.73
     AVG
    -0.71
    Review
    -0.71
    CLASSIFIED
    -0.71
    ATE
    -0.70
    EAR
    -0.70
    ESSION
    -0.70
    POSITIVE LOGITS
    oglobin
    1.45
     hem
    1.42
    isphere
    1.16
    odynam
    1.12
    odynamic
    1.08
     tiss
    1.00
    isp
    0.98
     lobe
    0.97
    iola
    0.95
    iza
    0.91
    Activations Density 0.007%

    No Known Activations