© 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. 2600
    Prev
    Next
    INDEX
    Explanations

    word and phrases related to membership or belonging

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate membership or affiliation

    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
    ptive
    -0.74
    vable
    -0.67
    case
    -0.67
    zers
    -0.66
    agnar
    -0.65
    zzle
    -0.65
     blush
    -0.64
    rollers
    -0.63
    headed
    -0.63
    ctive
    -0.62
    POSITIVE LOGITS
     sorts
    1.30
     hers
    1.03
     ours
    0.94
     theirs
    0.90
     mine
    0.83
     Nanto
    0.79
     yours
    0.76
     Peaks
    0.74
     srfAttach
    0.71
    Camp
    0.70
    Activations Density 0.153%

    No Known Activations