© 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. 6247
    Prev
    Next
    INDEX
    Explanations

    phrases expressing that something is essentially no more than something else

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the words "nothing more" or "nothing less."

    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
    days
    -0.64
     Fires
    -0.64
    oak
    -0.62
    xtap
    -0.61
     Bridges
    -0.61
     Advertisement
    -0.58
    maximum
    -0.58
     stumble
    -0.58
     shuffle
    -0.57
    stown
    -0.56
    POSITIVE LOGITS
     akin
    0.92
     than
    0.90
     resembling
    0.87
     manageable
    0.75
    ient
    0.75
     achievable
    0.74
     nor
    0.70
     nutrit
    0.69
    ntil
    0.68
    than
    0.68
    Activations Density 0.040%

    No Known Activations