© 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. 0-RES-JB
    11. 4921
    Prev
    Next
    INDEX
    Explanations

    instances of the word "phone" along with relevant contexts in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to mobile phones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hend
    -0.71
    Ëľ
    -0.70
    ankind
    -0.69
    м
    -0.68
    lore
    -0.66
    origin
    -0.66
    Ô
    -0.65
     Herbert
    -0.65
    ilib
    -0.65
    atics
    -0.64
    POSITIVE LOGITS
     phone
    3.59
     telephone
    2.69
     phones
    2.60
     Phone
    2.58
    phone
    2.52
    Phone
    2.43
     cellphone
    2.18
     Telephone
    1.99
     smartphone
    1.96
    phones
    1.90
    Activations Density 0.017%

    No Known Activations