© 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. 1-RES-JB
    11. 18027
    Prev
    Next
    INDEX
    Explanations

    words related to physical or abstract assaults

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "vault" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mos
    -0.67
     Ryu
    -0.63
     à¨
    -0.61
    ALE
    -0.59
     straw
    -0.59
     appealing
    -0.59
     Chandra
    -0.57
     shar
    -0.57
    ĻĤ
    -0.56
    NZ
    -0.56
    POSITIVE LOGITS
    ault
    1.53
    aults
    1.37
    eus
    0.90
    IER
    0.86
    ilege
    0.83
    ier
    0.80
    ily
    0.78
    iere
    0.77
    iliary
    0.76
    naire
    0.73
    Activations Density 0.007%

    No Known Activations