© 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. 3-RES-JB
    11. 12015
    Prev
    Next
    INDEX
    Explanations

    phrases with the term "vice versa"

    oai_token-act-pair · gpt-3.5-turbo

    instances of reciprocal relationships or oppositional concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ASE
    -0.65
    warning
    -0.60
     History
    -0.59
    ayn
    -0.59
     RIS
    -0.59
     synopsis
    -0.59
     Annotations
    -0.57
    agin
    -0.57
    gotten
    -0.57
     Glory
    -0.56
    POSITIVE LOGITS
     versa
    1.23
    entimes
    0.96
    dayName
    0.89
    forth
    0.74
    ossal
    0.72
    iless
    0.70
    forward
    0.70
    ministic
    0.69
    etheless
    0.69
    ratulations
    0.67
    Activations Density 0.008%

    No Known Activations