© 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. 17386
    Prev
    Next
    INDEX
    Explanations

    words related to impact or success, particularly in a positive sense

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "hit" 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
    æĢ
    -0.67
    idge
    -0.66
    UTH
    -0.63
    inent
    -0.63
    ignty
    -0.63
    çĶŁ
    -0.62
    agin
    -0.62
    uth
    -0.60
    aer
    -0.59
    eur
    -0.59
    POSITIVE LOGITS
    ched
    1.42
    ches
    1.06
     puberty
    0.98
    boxes
    0.94
     hardest
    0.91
     rock
    0.83
    ropolis
    0.82
    usalem
    0.79
     harder
    0.79
    achi
    0.78
    Activations Density 0.031%

    No Known Activations