© 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. 7-RES-JB
    11. 17764
    Prev
    Next
    INDEX
    Explanations

    longer words with an emphasis on the end letter

    oai_token-act-pair · gpt-3.5-turbo

    prefixes related to negation or opposition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Extras
    -0.81
     Rica
    -0.77
    姫
    -0.75
    terday
    -0.70
     Favor
    -0.68
     Hearts
    -0.67
     Ventures
    -0.67
     Sachs
    -0.66
    DragonMagazine
    -0.66
    edIn
    -0.65
    POSITIVE LOGITS
    iest
    1.45
    liest
    1.32
    osphere
    1.19
    hest
    1.14
    est
    1.12
    arest
    1.06
    cients
    1.00
    most
    0.99
    lest
    0.97
    archy
    0.94
    Activations Density 0.313%

    No Known Activations