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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16501
    Prev
    Next
    INDEX
    Explanations

    fax-related terms and mentions

    oai_token-act-pair · gpt-3.5-turbo
    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
    starter
    -0.83
    rency
    -0.81
    rencies
    -0.76
    emouth
    -0.73
    Kal
    -0.72
    ainer
    -0.72
     unl
    -0.71
     Noble
    -0.71
    NER
    -0.70
     Wallet
    -0.69
    POSITIVE LOGITS
     wax
    2.44
     fax
    2.09
     Wax
    1.84
     pap
    1.54
    Fax
    1.33
     annex
    1.27
     Hut
    1.17
     transcription
    1.17
     cler
    1.02
     tub
    1.02
    Activations Density 0.057%

    No Known Activations