© 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. 7-RES-JB
    11. 2265
    Prev
    Next
    INDEX
    Explanations

    names that end with 'ust' or 'ent'

    oai_token-act-pair · gpt-3.5-turbo

    unique affixes or word components that may indicate important names or terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     steep
    -0.57
    ships
    -0.56
     Disciple
    -0.56
    pton
    -0.55
     AFL
    -0.54
     Stub
    -0.54
    TRY
    -0.54
    Pear
    -0.53
     Ricardo
    -0.53
     adm
    -0.52
    POSITIVE LOGITS
    rals
    0.89
    inen
    0.88
    inis
    0.87
    insky
    0.83
    opol
    0.82
    nikov
    0.81
    opoulos
    0.81
    chev
    0.80
    nis
    0.80
    ioch
    0.80
    Activations Density 0.178%

    No Known Activations