© 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. 6-RES-JB
    11. 21756
    Prev
    Next
    INDEX
    Explanations

    references to technological terms related to computers or command lines

    oai_token-act-pair · gpt-3.5-turbo

    references to terminal commands and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yer
    -0.87
    akening
    -0.85
    itsch
    -0.83
    sky
    -0.79
    resh
    -0.78
    ered
    -0.78
    indu
    -0.76
    aven
    -0.74
    lesh
    -0.74
    Ĭ
    -0.73
    POSITIVE LOGITS
     emulator
    1.10
     terminal
    1.08
     terminals
    0.92
     Terminal
    0.84
     velocity
    0.74
    TY
    0.74
     mosqu
    0.69
    igmatic
    0.68
     checkout
    0.67
    ysis
    0.67
    Activations Density 0.026%

    No Known Activations