© 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. 1-RES-JB
    11. 14359
    Prev
    Next
    INDEX
    Explanations

    words related to technology and software, particularly including terms like "XT", "LT", and "NXT"

    oai_token-act-pair · gpt-3.5-turbo

    references to technological terms and designations, particularly in the context of digital platforms and applications

    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
     Clicker
    -0.68
    tz
    -0.65
     rabbit
    -0.64
    Reviewer
    -0.63
     behavi
    -0.61
    hound
    -0.61
     casualty
    -0.61
     pick
    -0.60
     deceive
    -0.60
     agent
    -0.60
    POSITIVE LOGITS
    XT
    1.16
    ribute
    1.09
    ension
    0.96
    ECH
    0.95
    ENTION
    0.93
    ensions
    0.93
    arios
    0.92
    reme
    0.92
    amen
    0.91
    ainted
    0.89
    Activations Density 0.029%

    No Known Activations