© 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. 6974
    Prev
    Next
    INDEX
    Explanations

    patterns that include the letters "le" at a particular position within a word

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "le" in various contexts

    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
    ortion
    -0.76
     recess
    -0.67
     clock
    -0.65
    ãģĨ
    -0.63
    ����
    -0.63
     proportional
    -0.60
     JR
    -0.60
     instrument
    -0.59
    ãĥ¼ãĥĨãĤ£
    -0.59
     CoC
    -0.57
    POSITIVE LOGITS
    isure
    1.42
    agues
    1.34
    ukemia
    1.33
    ather
    1.27
    aving
    1.26
    icester
    1.24
    opard
    1.23
    aky
    1.13
    aves
    1.12
    aked
    1.10
    Activations Density 0.027%

    No Known Activations