© 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. 13218
    Prev
    Next
    INDEX
    Explanations

    verbs or phrases indicating an action or state

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "to be" in different forms

    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
     DOI
    -0.66
     Seasons
    -0.61
    Footnote
    -0.60
    verts
    -0.59
    itches
    -0.59
    sted
    -0.58
    erald
    -0.57
    oso
    -0.56
    asers
    -0.56
     Rates
    -0.56
    POSITIVE LOGITS
     happening
    1.38
     occurring
    1.05
     unfolding
    0.89
     achievable
    0.89
     transpired
    0.87
     wrong
    0.87
     going
    0.87
     supposed
    0.86
     bothering
    0.84
     done
    0.81
    Activations Density 0.087%

    No Known Activations