© 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. 10-RES-JB
    11. 12304
    Prev
    Next
    INDEX
    Explanations

    city names

    oai_token-act-pair · gpt-3.5-turbo

    slang terms or playful expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scrambled
    -0.66
    ICAN
    -0.63
    theless
    -0.60
     concess
    -0.59
     congr
    -0.59
    erity
    -0.59
    OTOS
    -0.58
     Tanz
    -0.58
     Samar
    -0.58
    romeda
    -0.56
    POSITIVE LOGITS
    odan
    1.08
    inki
    0.89
    estyle
    0.87
    itzer
    0.82
    eways
    0.81
    rock
    0.79
    dog
    0.79
    llan
    0.78
    vik
    0.77
    tarian
    0.77
    Activations Density 0.110%

    No Known Activations