© 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. 6-RES-JB
    11. 14475
    Prev
    Next
    INDEX
    Explanations

    references to reaching out for communication

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "reached out to"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾įåĸļ士
    -0.81
    jing
    -0.72
    sterdam
    -0.70
    mpeg
    -0.69
    cake
    -0.69
    ivari
    -0.67
    busters
    -0.67
    Grad
    -0.64
    Fall
    -0.62
    rats
    -0.62
    POSITIVE LOGITS
     inquire
    0.86
     solicit
    0.85
     clarify
    0.78
     nominate
    0.77
     reassure
    0.77
     invite
    0.75
     elicit
    0.72
    otin
    0.66
     help
    0.65
     investigate
    0.65
    Activations Density 0.039%

    No Known Activations