© 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. 10-RES-JB
    11. 10600
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussions about feasibility and risks, often involving quotes from speakers

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks used in dialogue or to indicate pauses in conversation

    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
    ãĥīãĥ©
    -0.77
    ãĥĻ
    -0.74
    ãĤ¦ãĤ¹
    -0.72
    chnology
    -0.69
    xxxx
    -0.68
    ãĤ©
    -0.67
    ãģł
    -0.66
    etheless
    -0.65
    agin
    -0.65
    ãĥ¯ãĥ³
    -0.64
    POSITIVE LOGITS
     he
    1.65
     she
    1.41
     said
    1.08
    she
    1.03
     Mr
    0.92
     He
    0.91
     according
    0.88
    He
    0.87
    said
    0.86
    he
    0.84
    Activations Density 0.282%

    No Known Activations