© 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. 11-RES-JB
    11. 18767
    Prev
    Next
    INDEX
    Explanations

    phrases indicating possibility or capability

    oai_token-act-pair · gpt-3.5-turbo

    instances of the modal verb "can" indicating possibilities or abilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Seeking
    -0.67
     Hamp
    -0.61
    lication
    -0.60
    PDATE
    -0.58
     Ready
    -0.58
     Creed
    -0.57
     Peb
    -0.56
     mosqu
    -0.56
     Tradition
    -0.55
     Mandatory
    -0.55
    POSITIVE LOGITS
    't
    1.53
     be
    1.08
     exacerbate
    1.03
     vary
    1.03
    isters
    1.01
     easily
    0.99
     sometimes
    0.99
     complicate
    0.99
     distort
    0.98
     confuse
    0.96
    Activations Density 0.087%

    No Known Activations