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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2-RES-JB
    6. 23927
    Prev
    Next
    INDEX
    Explanations

    words related to pulses or heartbeats: 'pulse', 'pulse', 'pulse', 'pulse', 'pulse', 'pulse', 'pulse', 'pulse', 'pulse', 'pulse', 'pulse', 'pulse', 'Pulse', 'Pulse', 'Pulse', 'Pulse

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "pulse" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sask
    -0.76
    BuyableInstoreAndOnline
    -0.73
    sm
    -0.69
    sle
    -0.65
    ãģĤ
    -0.64
    OULD
    -0.63
    AME
    -0.62
    adr
    -0.62
    YA
    -0.60
    sie
    -0.60
    POSITIVE LOGITS
     pulse
    1.09
    ulse
    1.01
    beam
    0.98
     pulses
    0.92
     puls
    0.90
    audio
    0.85
    oleon
    0.76
     Width
    0.75
    isode
    0.74
    ²¾
    0.73
    Activations Density 0.008%

    No Known Activations