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

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 1028
    Prev
    Next
    INDEX
    Explanations

    specific qualities or attributes such as physical characteristics, states, or actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various forms of measurement and evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    >>\
    -0.68
    Newsletter
    -0.66
    é¾į
    -0.65
     Sunshine
    -0.63
    enance
    -0.61
     Staten
    -0.60
    otonin
    -0.59
    iggurat
    -0.58
    election
    -0.58
     Shore
    -0.56
    POSITIVE LOGITS
    wise
    1.07
    esides
    0.97
    pecially
    0.93
    ardless
    0.89
     wise
    0.87
    cause
    0.86
    itatively
    0.81
    cially
    0.77
    ially
    0.75
     notwithstanding
    0.74
    Activations Density 0.617%

    No Known Activations