© 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. 8-RES-JB
    11. 22340
    Prev
    Next
    INDEX
    Explanations

    Twitter-like post captions containing hashtags

    oai_token-act-pair · gpt-3.5-turbo

    hashtags or labels associated with content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    boro
    -0.73
     staggered
    -0.67
     cler
    -0.65
     bung
    -0.64
     Ortiz
    -0.64
     Deng
    -0.62
     Wander
    -0.62
     Chic
    -0.62
     Pilgrim
    -0.61
    aukee
    -0.60
    POSITIVE LOGITS
    ########
    1.19
    ################################
    1.17
    ################
    1.01
    ###
    0.97
    region
    0.87
    MENTS
    0.84
    Reply
    0.84
    define
    0.80
    why
    0.80
    ANN
    0.80
    Activations Density 0.013%

    No Known Activations