© 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. 0-RES-JB
    11. 7863
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific person's name

    oai_token-act-pair · gpt-3.5-turbo

    the term "ero" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inst
    -0.69
     jewel
    -0.66
     counts
    -0.65
     divisions
    -0.63
     tit
    -0.63
     alarmed
    -0.62
     plural
    -0.61
     Hunger
    -0.58
     doub
    -0.58
     mosques
    -0.58
    POSITIVE LOGITS
    ero
    4.85
    eros
    2.00
    ERO
    1.78
    eria
    1.48
    era
    1.46
    eno
    1.12
    eri
    1.11
    ado
    1.10
    elo
    1.08
    esta
    1.07
    Activations Density 0.011%

    No Known Activations