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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 10-RES-JB
    6. 3424
    Prev
    Next
    INDEX
    Explanations

    words related to speed or lack thereof

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the word "slow."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ortium
    -0.89
    çīĪ
    -0.81
    illon
    -0.74
    ITION
    -0.74
    IDA
    -0.72
    osate
    -0.71
    arov
    -0.70
    ALD
    -0.69
    Bet
    -0.68
    -+-+
    -0.68
    POSITIVE LOGITS
    poke
    1.31
     cooker
    1.27
    downs
    1.25
     paced
    1.12
     pace
    1.02
    down
    1.01
     speeds
    0.92
     tempo
    0.92
    est
    0.91
     motion
    0.89
    Activations Density 0.045%

    No Known Activations