© 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. 6866
    Prev
    Next
    INDEX
    Explanations

    references to providing, offering, or giving something

    oai_token-act-pair · gpt-3.5-turbo

    key terms and phrases related to governance and politics

    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
    asha
    -0.74
    awaru
    -0.65
    iffe
    -0.60
    è¦
    -0.60
     Cosponsors
    -0.60
    soType
    -0.59
    wcsstore
    -0.59
    anwhile
    -0.58
    gra
    -0.58
     attm
    -0.58
    POSITIVE LOGITS
     plenty
    1.06
     permission
    1.04
     ample
    1.03
     something
    0.91
     an
    0.89
     access
    0.87
     a
    0.86
     some
    0.83
     pause
    0.83
     considerable
    0.82
    Activations Density 0.265%

    No Known Activations