© 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. 2-RES-JB
    11. 18363
    Prev
    Next
    INDEX
    Explanations

    names that end in "ins"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the suffix "ins"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¶ħ
    -0.79
     compr
    -0.72
    ŃĶ
    -0.70
    ģĸ
    -0.69
    £ı
    -0.69
    è¦ļéĨĴ
    -0.69
     Sigma
    -0.68
     Reconstruction
    -0.67
    ¿½
    -0.67
     Reason
    -0.67
    POSITIVE LOGITS
    pection
    1.14
    pect
    1.13
    urance
    1.10
    urg
    1.06
    anity
    1.02
    piration
    1.01
    uit
    1.00
    ufficient
    0.99
    ensitive
    0.99
    strument
    0.94
    Activations Density 0.014%

    No Known Activations