© 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. 3-RES-JB
    11. 10790
    Prev
    Next
    INDEX
    Explanations

    words related to a specific disease or medical condition

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the abbreviation "CL" followed by numerical values or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fitting
    -0.80
    ãĥĦ
    -0.79
    tale
    -0.78
    ãĤ¹ãĥĪ
    -0.77
    sov
    -0.76
    elsen
    -0.75
    ãĤ®
    -0.74
    ãĥ´ãĤ¡
    -0.73
    ka
    -0.73
    catch
    -0.72
    POSITIVE LOGITS
    INTON
    1.10
    OSED
    1.07
    IENT
    1.01
    OCK
    0.95
    IFF
    0.88
    OTH
    0.87
    ANN
    0.86
    avier
    0.85
    OWER
    0.84
    ister
    0.84
    Activations Density 0.007%

    No Known Activations