© 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. 8-RES-JB
    11. 1357
    Prev
    Next
    INDEX
    Explanations

    proper nouns that start with a capital letter followed by a high concentration of capital letters within the token

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and specific titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aisle
    -0.72
     carriers
    -0.71
     carrier
    -0.70
     stalk
    -0.69
     trademark
    -0.63
     controllers
    -0.63
     generals
    -0.62
     corners
    -0.61
     pedal
    -0.60
     controller
    -0.60
    POSITIVE LOGITS
    acia
    0.73
    ild
    0.69
    izont
    0.67
    nergy
    0.66
    OTOS
    0.66
    Op
    0.66
    UE
    0.66
    orama
    0.66
    Keys
    0.66
    obal
    0.65
    Activations Density 0.255%

    No Known Activations