© 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. 1-RES-JB
    11. 5580
    Prev
    Next
    INDEX
    Explanations

    dialog-related terms or technology-related contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "dialog" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IFT
    -0.89
    EEE
    -0.78
    ADA
    -0.78
    theless
    -0.73
    ITE
    -0.72
    STD
    -0.71
    1500
    -0.70
    ulz
    -0.69
    USE
    -0.68
    ACK
    -0.68
    POSITIVE LOGITS
     dialog
    1.26
    ues
    1.05
    log
    0.93
    dial
    0.92
    Dialog
    0.91
    orer
    0.90
    ophe
    0.85
     Dial
    0.83
    oad
    0.83
     dialogue
    0.83
    Activations Density 0.004%

    No Known Activations