© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 3476
    Prev
    Next
    INDEX
    Explanations

    word combinations related to fictional characters and their actions

    oai_token-act-pair · gpt-3.5-turbo

    references to pop culture figures and themes related to justice and social commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    currently
    -0.73
     Adin
    -0.72
    ickr
    -0.72
    iov
    -0.71
     USE
    -0.69
    amina
    -0.69
    argo
    -0.68
     SEN
    -0.67
    earcher
    -0.66
     [+
    -0.65
    POSITIVE LOGITS
    esque
    1.15
    âĦ¢
    0.94
     Syndrome
    0.92
    Ħ¢
    0.84
     proportions
    0.82
    style
    0.80
     Award
    0.80
     sensibilities
    0.79
     ®
    0.78
     sneakers
    0.78
    Activations Density 0.812%

    No Known Activations