© 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. 2176
    Prev
    Next
    INDEX
    Explanations

    phrases related to contrasting or emphasizing information

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases that include the word "this" followed by a variety of common conjunctions or prepositions

    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
     href
    -0.58
    agall
    -0.57
     appro
    -0.57
    GI
    -0.54
    ga
    -0.53
     Near
    -0.52
     pickup
    -0.52
     abduct
    -0.52
    gd
    -0.51
     Names
    -0.51
    POSITIVE LOGITS
     coupled
    0.94
     notwithstanding
    0.80
     however
    0.74
     incidentally
    0.73
    along
    0.72
     sadly
    0.71
     besides
    0.71
     combined
    0.70
     alas
    0.69
     suffice
    0.68
    Activations Density 0.070%

    No Known Activations