© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 11538
    Prev
    Next
    INDEX
    Explanations

    words related to specific names, potentially surnames or proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "iber" and variations related to it

    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
    atche
    -0.71
    ĸļ
    -0.70
     pity
    -0.64
    urations
    -0.63
     parcels
    -0.62
     ath
    -0.62
    plings
    -0.62
    ŃĶ
    -0.61
    isters
    -0.59
     Papua
    -0.59
    POSITIVE LOGITS
    tarian
    1.10
    tarians
    1.07
    glass
    0.93
    nation
    0.91
    gence
    0.85
    ulent
    0.84
    nia
    0.81
    leness
    0.77
    ALLY
    0.77
    glas
    0.76
    Activations Density 0.033%

    No Known Activations