© 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. 17141
    Prev
    Next
    INDEX
    Explanations

    the verb "be" and related forms

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating predictions or assessments about future events

    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
    76561
    -0.69
    allows
    -0.68
    DragonMagazine
    -0.65
    airo
    -0.64
    éĹĺ
    -0.63
    orsi
    -0.62
    enary
    -0.61
    luaj
    -0.59
    })
    -0.59
    ertodd
    -0.58
    POSITIVE LOGITS
     awhile
    1.22
     interesting
    1.15
     tempting
    1.13
     fun
    1.13
     easier
    1.04
     difficult
    1.02
     worthwhile
    1.00
     fascinating
    0.99
     raining
    0.98
     nice
    0.98
    Activations Density 0.095%

    No Known Activations