© 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. 4042
    Prev
    Next
    INDEX
    Explanations

    contact or general information such as email addresses and details about events

    oai_token-act-pair · gpt-3.5-turbo

    phrases and expressions related to information or details

    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
     successive
    -0.66
     McDonnell
    -0.66
    teenth
    -0.65
    hift
    -0.64
    flation
    -0.63
    egal
    -0.63
    awed
    -0.62
    azo
    -0.62
    ½
    -0.61
    amorph
    -0.60
    POSITIVE LOGITS
     info
    3.50
     Info
    2.32
     information
    2.08
    info
    2.06
     INFO
    1.83
    Info
    1.81
     INFORMATION
    1.70
     intel
    1.68
    information
    1.67
     Information
    1.52
    Activations Density 0.012%

    No Known Activations