© 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. 10-RES-JB
    11. 23204
    Prev
    Next
    INDEX
    Explanations

    phrases indicating emphasis or comparison

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the word "nothing" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CVE
    -0.67
    ippers
    -0.67
    essing
    -0.65
    ardi
    -0.64
    orf
    -0.64
    oise
    -0.63
    oak
    -0.63
    RAFT
    -0.62
    orks
    -0.62
     Shutterstock
    -0.61
    POSITIVE LOGITS
     else
    1.26
    Else
    1.19
     happens
    1.07
     happened
    1.05
     lasts
    1.00
     Else
    0.94
     resembling
    0.89
     justifies
    0.88
     prevents
    0.87
     remotely
    0.86
    Activations Density 0.046%

    No Known Activations