© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 623
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers representing positions

    oai_token-act-pair · gpt-3.5-turbo

    ordinal numbers and their variations

    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
    è¦ļéĨĴ
    -0.70
    Leader
    -0.69
    Mobil
    -0.69
    Reward
    -0.68
    Magikarp
    -0.68
    Je
    -0.67
    rooms
    -0.66
    drawn
    -0.65
    HAHAHAHA
    -0.64
    Boost
    -0.64
    POSITIVE LOGITS
    ieth
    1.15
     tenth
    0.89
     inning
    0.86
    eenth
    0.82
    ulhu
    0.76
    sie
    0.76
    ãĤ©
    0.74
     eighth
    0.74
    ursday
    0.72
    onso
    0.72
    Activations Density 0.005%

    No Known Activations