© 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. 9-RES-JB
    11. 16242
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a change or continuation in a narrative

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "after" used to indicate a temporal reference or sequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     constitu
    -0.84
    MENT
    -0.80
    Location
    -0.72
    女
    -0.70
     guiActiveUn
    -0.69
     endif
    -0.68
    tick
    -0.68
    IZE
    -0.68
    onds
    -0.67
    ASE
    -0.66
    POSITIVE LOGITS
     decades
    1.02
    noon
    0.97
     years
    0.92
     awhile
    0.89
     centuries
    0.89
     witnessing
    0.88
     careful
    0.87
     losing
    0.86
     exhaustive
    0.85
     enduring
    0.85
    Activations Density 0.109%

    No Known Activations