© 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. 2-RES-JB
    11. 3912
    Prev
    Next
    INDEX
    Explanations

    phrases and sentences with the expression "on the other hand"

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases contrasting two sides or perspectives

    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
    avorite
    -0.90
    alach
    -0.68
    encers
    -0.66
    quartered
    -0.65
    omorph
    -0.64
    ngth
    -0.64
    umph
    -0.64
     reliant
    -0.64
    RIC
    -0.63
    amic
    -0.62
    POSITIVE LOGITS
     occasions
    0.98
     heels
    0.93
     eve
    0.91
     rooft
    0.82
     forums
    0.81
     Spectrum
    0.76
     assumption
    0.76
     basis
    0.75
     occasion
    0.74
     periphery
    0.73
    Activations Density 0.891%

    No Known Activations