Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 19281
    Prev
    Next
    INDEX
    Explanations

    Twitter handles

    oai_token-act-pair · gpt-3.5-turbo

    specific social media handles or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Contra
    -0.89
     defic
    -0.81
     Antar
    -0.80
     Instr
    -0.76
     Reyn
    -0.74
    ENE
    -0.73
    409
    -0.71
     Trace
    -0.70
     resil
    -0.70
     Frag
    -0.70
    POSITIVE LOGITS
    k
    1.67
    ke
    1.54
    ks
    1.51
    ked
    1.50
    ka
    1.48
    kas
    1.48
    K
    1.47
    kan
    1.45
    KA
    1.42
    ket
    1.41
    Activations Density 0.356%

    No Known Activations