© 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. 12767
    Prev
    Next
    INDEX
    Explanations

    phrases related to the strength or resilience of something, often with the word "the" preceding it

    oai_token-act-pair · gpt-3.5-turbo

    frequent use of the word "the"

    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
    vl
    -0.83
    autions
    -0.79
    imity
    -0.77
    icia
    -0.77
    erity
    -0.75
    fulness
    -0.74
    ptions
    -0.71
    abel
    -0.70
    worth
    -0.70
    earance
    -0.70
    POSITIVE LOGITS
     respective
    0.92
     entire
    0.88
     cosmos
    0.88
     individual
    0.88
     profession
    0.87
     preceding
    0.86
     sexes
    0.85
     wearer
    0.85
     nation
    0.85
     universe
    0.85
    Activations Density 0.310%

    No Known Activations