© 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. 3751
    Prev
    Next
    INDEX
    Explanations

    exclamatory statements expressing strong emotions

    oai_token-act-pair · gpt-3.5-turbo

    exclamations or strong emotional expressions

    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
     conduc
    -0.85
    uter
    -0.71
    undai
    -0.70
    senal
    -0.70
    yrus
    -0.68
     contracted
    -0.67
    idon
    -0.67
     destro
    -0.66
    allas
    -0.64
     fielded
    -0.64
    POSITIVE LOGITS
    @#&
    1.38
    #$
    1.19
    ?!
    1.13
    @#
    1.02
    ãĢį
    0.97
    important
    0.88
     Surely
    0.79
     Somebody
    0.77
    oops
    0.76
     Euph
    0.74
    Activations Density 0.068%

    No Known Activations