© 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. 20258
    Prev
    Next
    INDEX
    Explanations

    phrases related to moral or ethical considerations

    oai_token-act-pair · gpt-3.5-turbo

    legal terminology related to crime and consequences

    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
    htaking
    -0.57
     lately
    -0.54
    ĸļ
    -0.54
     wore
    -0.53
    uli
    -0.53
     acron
    -0.52
    endiary
    -0.51
     recently
    -0.50
     coincided
    -0.50
    ©¶æ
    -0.50
    POSITIVE LOGITS
    morrow
    0.72
     worthless
    0.68
     wiser
    0.68
     forever
    0.63
     downstream
    0.62
     indefinitely
    0.60
     automatically
    0.58
     useless
    0.57
     anyway
    0.57
     poorer
    0.56
    Activations Density 1.640%

    No Known Activations