Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 19848
    Prev
    Next
    INDEX
    Explanations

    expressions of strong emotion or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    exclamatory statements expressing strong emotions or frustrations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     conduc
    -0.86
    yrus
    -0.78
     destro
    -0.73
    idon
    -0.72
     contracted
    -0.70
    undai
    -0.69
    matically
    -0.66
     skelet
    -0.64
    allas
    -0.64
    uter
    -0.63
    POSITIVE LOGITS
    @#&
    1.31
    #$
    1.23
    ?!
    1.09
    @#
    1.01
    ãĢį
    0.91
     Surely
    0.86
    important
    0.84
     Somebody
    0.80
     Come
    0.75
     Needless
    0.74
    Activations Density 0.069%

    No Known Activations