© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 9199
    Prev
    Next
    INDEX
    Explanations

    actions involving the act of going through a process or system

    oai_token-act-pair · gpt-3.5-turbo

    prepositions indicating a method or means of communication or transaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nesota
    -0.84
    worth
    -0.73
     behold
    -0.71
    Synopsis
    -0.68
    ongevity
    -0.67
    isel
    -0.67
    otype
    -0.66
     illustrating
    -0.66
    ###
    -0.64
    hiro
    -0.64
    POSITIVE LOGITS
     intermedi
    0.89
     channels
    0.87
     intermediary
    0.80
     pipelines
    0.79
     networks
    0.78
     Nex
    0.76
     HTTPS
    0.76
     conduit
    0.75
     PayPal
    0.74
     Rout
    0.74
    Activations Density 0.189%

    No Known Activations