Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 9135
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical attributes or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    sentences or phrases with high punctuation density

    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
     divest
    -0.92
    anche
    -0.86
     advocate
    -0.82
     unsuccessful
    -0.82
     eligibility
    -0.82
     credential
    -0.81
     authorized
    -0.81
     banned
    -0.81
     national
    -0.80
     advis
    -0.80
    POSITIVE LOGITS
     Also
    1.27
     Seems
    1.22
     Looks
    1.22
     Anyway
    1.22
     Lots
    1.18
     Thankfully
    1.15
     Basically
    1.13
     Quite
    1.13
     Compared
    1.12
     Luckily
    1.11
    Activations Density 0.458%

    No Known Activations