© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 17063
    Prev
    Next
    INDEX
    Explanations

    phrases related to management, planning, and enforcement

    oai_token-act-pair · gpt-3.5-turbo

    connections between statements and their implications

    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
    sole
    -0.76
     repe
    -0.71
     delighted
    -0.66
     nostalgic
    -0.65
     gigg
    -0.65
     flavored
    -0.65
    ozyg
    -0.64
     pard
    -0.64
     congrat
    -0.63
     affiliate
    -0.63
    POSITIVE LOGITS
     Otherwise
    1.65
     Ideally
    1.34
    Otherwise
    1.32
     preferably
    1.20
     Luckily
    1.02
     Secondly
    0.97
     ideally
    0.96
     Fortunately
    0.95
    Secondly
    0.93
     Thankfully
    0.91
    Activations Density 0.552%

    No Known Activations