© 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. 1-RES-JB
    11. 9422
    Prev
    Next
    INDEX
    Explanations

    Russian characters indicating a specific pattern or style

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols from a specific language or encoding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nels
    -0.76
     Raleigh
    -0.64
     Hunts
    -0.64
    enegger
    -0.64
    Lear
    -0.64
    culosis
    -0.63
     hazard
    -0.63
     Leap
    -0.63
    ndra
    -0.63
    neys
    -0.63
    POSITIVE LOGITS
    Ñ
    1.60
    ħ
    1.40
    ķ
    1.33
    ĩ
    1.33
    Ħ
    1.28
    Ķ
    1.23
    ĺ
    1.23
    Ĩ
    1.22
    Ī
    1.21
    о
    1.20
    Activations Density 0.001%

    No Known Activations