© 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. 6-RES-JB
    11. 20417
    Prev
    Next
    INDEX
    Explanations

    websites URLs containing 's'

    oai_token-act-pair · gpt-3.5-turbo

    empty or whitespace tokens indicating a lack of content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĥĨ
    -0.79
     behavi
    -0.79
     thous
    -0.76
     hemor
    -0.76
     compar
    -0.71
     visitation
    -0.65
     pree
    -0.65
     Leilan
    -0.64
     mileage
    -0.63
     misunder
    -0.62
    POSITIVE LOGITS
    ouls
    1.08
    wered
    1.03
    acks
    1.02
    arah
    1.01
    olo
    0.99
    alt
    0.99
    anta
    0.98
    ued
    0.98
    ushi
    0.97
    aved
    0.96
    Activations Density 0.042%

    No Known Activations