© 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. 11674
    Prev
    Next
    INDEX
    Explanations

    medical terms related to conditions or diseases

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "guilt" and its variations

    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
     compr
    -0.74
    lished
    -0.73
    EStream
    -0.67
    ©¶æ
    -0.67
     gobl
    -0.66
    oÄŁ
    -0.66
    ccording
    -0.66
    BOOK
    -0.65
    linux
    -0.65
    İĭ
    -0.64
    POSITIVE LOGITS
    espie
    1.39
    uminati
    1.35
    iard
    1.15
    icit
    1.09
    inois
    1.04
    omon
    0.97
    ustration
    0.97
    umin
    0.95
    igan
    0.94
    usions
    0.93
    Activations Density 0.027%

    No Known Activations