© 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. 8-RES-JB
    11. 6556
    Prev
    Next
    INDEX
    Explanations

    instances where the letter "l" is preceded by another letter or letters

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'l'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chell
    -0.67
    ãĥ¯ãĥ³
    -0.66
    ãĥ¼ãĥĨãĤ£
    -0.64
    OLOGY
    -0.63
    éĹĺ
    -0.63
     Lit
    -0.62
    lished
    -0.61
     Rule
    -0.60
     Primal
    -0.60
     Credit
    -0.60
    POSITIVE LOGITS
    ibrarian
    1.38
    adders
    1.37
    ibr
    1.31
    ongh
    1.19
    onel
    1.18
    ivery
    1.17
    izards
    1.15
    otto
    1.13
    idd
    1.12
    opez
    1.11
    Activations Density 0.025%

    No Known Activations