© 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. 0-RES-JB
    11. 23245
    Prev
    Next
    INDEX
    Explanations

    instances of comebacks or resurgence

    oai_token-act-pair · gpt-3.5-turbo

    mentions of comebacks or revivals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administ
    -0.65
    SI
    -0.65
    Materials
    -0.63
     instructed
    -0.62
     provisions
    -0.60
     Anat
    -0.60
    agents
    -0.60
    ages
    -0.60
    gat
    -0.59
     described
    -0.58
    POSITIVE LOGITS
     comeback
    3.84
     resurgence
    1.64
     revival
    1.60
     turnaround
    1.43
     renaissance
    1.35
     rebound
    1.25
     rematch
    1.22
     recovery
    1.20
     cameo
    1.20
     reunion
    1.17
    Activations Density 0.013%

    No Known Activations