© 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. 1559
    Prev
    Next
    INDEX
    Explanations

    phrases related to sales transactions or sales activities

    oai_token-act-pair · gpt-3.5-turbo

    references to sales statistics and metrics

    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
    icz
    -0.75
    atever
    -0.72
    --+
    -0.69
     Judicial
    -0.68
    ¯¯
    -0.65
    OSE
    -0.64
    anamo
    -0.63
    aque
    -0.61
     Leone
    -0.61
    oss
    -0.60
    POSITIVE LOGITS
    manship
    1.05
    force
    1.01
    people
    0.99
    person
    0.99
    hips
    0.96
    hare
    0.86
     receipts
    0.84
    women
    0.83
    pers
    0.82
    shop
    0.80
    Activations Density 0.036%

    No Known Activations