Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 23075
    Prev
    Next
    INDEX
    Explanations

    keywords related to numerical values, measurements, and technical specifications

    oai_token-act-pair · gpt-3.5-turbo

    numeric values

    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
    alid
    -0.85
    andering
    -0.82
    stra
    -0.80
    ogi
    -0.77
    icka
    -0.77
    chal
    -0.75
    iqu
    -0.75
    ored
    -0.74
    gotten
    -0.74
    ouri
    -0.72
    POSITIVE LOGITS
    mAh
    1.20
     MHz
    0.93
     Hz
    0.87
    MHz
    0.84
     rpm
    0.84
    +
    0.83
    é¾įåĸļ士
    0.81
     NOTICE
    0.81
     kcal
    0.79
    rpm
    0.77
    Activations Density 0.034%

    No Known Activations