© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 21125
    Prev
    Next
    INDEX
    Explanations

    phrases related to rankings or positions, often containing "No" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    rankings of players or teams in sports

    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
    endish
    -0.76
     destro
    -0.74
    redits
    -0.67
    iership
    -0.67
    RAFT
    -0.62
     trave
    -0.61
    romeda
    -0.59
    inese
    -0.58
     resemb
    -0.58
    FML
    -0.58
    POSITIVE LOGITS
    xious
    1.11
    obs
    0.89
    zzle
    0.85
    DIV
    0.85
     Matter
    0.81
    Such
    0.77
    emi
    0.76
    ERROR
    0.75
    onday
    0.75
    iron
    0.75
    Activations Density 0.030%

    No Known Activations