© 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. 19180
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence or involvement of something or someone

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "there" or relate to existence and presence

    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
    ás
    -0.72
    atown
    -0.66
     Hust
    -0.65
    elta
    -0.65
     Fiction
    -0.62
     Cuba
    -0.61
    rez
    -0.60
    utenberg
    -0.58
    ruct
    -0.58
     Journalism
    -0.58
    POSITIVE LOGITS
     consequently
    1.18
     accordingly
    1.06
     therefore
    0.97
     consequ
    0.90
     subsequent
    0.79
     alike
    0.79
     secondly
    0.77
     resultant
    0.77
     expects
    0.73
     ensuing
    0.73
    Activations Density 0.570%

    No Known Activations