© 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. 5327
    Prev
    Next
    INDEX
    Explanations

    names of individuals with a specific pattern in their names, where the last few letters are repeated in a sequence

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of individuals and locations

    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
    ufact
    -0.85
    ources
    -0.77
    INAL
    -0.74
    xual
    -0.71
    owship
    -0.69
    ctr
    -0.63
    ICES
    -0.63
    idav
    -0.59
    actionDate
    -0.58
    ICAN
    -0.58
    POSITIVE LOGITS
    abba
    0.63
    çİĭ
    0.61
    nova
    0.60
    bye
    0.60
    belt
    0.59
    orno
    0.59
    ashi
    0.58
    uni
    0.56
     Clouds
    0.56
    shine
    0.55
    Activations Density 0.341%

    No Known Activations