© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9260
    Prev
    Next
    INDEX
    Explanations

    comparative phrases denoting a higher level of something

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of the word "more" in various contexts

    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
    xtap
    -0.79
    atan
    -0.72
    uckle
    -0.69
    çļ
    -0.69
    IPS
    -0.69
    OCK
    -0.67
    upuncture
    -0.66
    UNCH
    -0.66
    onds
    -0.65
    oresc
    -0.65
    POSITIVE LOGITS
     than
    1.60
    than
    1.24
     akin
    1.05
     Than
    1.04
     suited
    1.00
     likely
    0.97
     complicated
    0.96
     inclined
    0.93
     efficient
    0.92
     importantly
    0.91
    Activations Density 0.095%

    No Known Activations