© 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. 8-RES-JB
    11. 22331
    Prev
    Next
    INDEX
    Explanations

    phrases related to the impact or effect of various actions or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases discussing the impact of various factors on society or specific sectors

    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
    ft
    -0.69
    cknowled
    -0.68
    atts
    -0.64
     drafts
    -0.59
    Ĥ¬
    -0.58
    Pie
    -0.57
    wagen
    -0.56
     Hedge
    -0.56
     sweats
    -0.56
     peas
    -0.55
    POSITIVE LOGITS
     multiplier
    0.82
     impacting
    0.82
     affecting
    0.81
     whatsoever
    0.77
    ulative
    0.76
    ktop
    0.76
    notation
    0.75
    iless
    0.75
    isSpecialOrderable
    0.74
     beyond
    0.73
    Activations Density 0.108%

    No Known Activations