© 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. 2-RES-JB
    11. 17075
    Prev
    Next
    INDEX
    Explanations

    terms related to provisional agreements or arrangements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to provisional or temporary statuses and duties

    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
    wig
    -0.91
    achus
    -0.83
    hammad
    -0.79
    ulhu
    -0.79
    holes
    -0.78
    gling
    -0.77
    gdala
    -0.77
    yre
    -0.77
    ħĭ
    -0.76
    psc
    -0.76
    POSITIVE LOGITS
     provisional
    1.41
    ourn
    0.72
     temporarily
    0.67
     brake
    0.65
     ceasefire
    0.65
     basis
    0.63
     stret
    0.61
     spoil
    0.61
     Karin
    0.61
     politic
    0.61
    Activations Density 0.007%

    No Known Activations