© 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. 4-RES-JB
    11. 6256
    Prev
    Next
    INDEX
    Explanations

    phrases related to bringing in people or things

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "bring in" along with its variations

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

    No Comments

    Negative Logits
    CLASSIFIED
    -0.76
    =]
    -0.68
    CVE
    -0.66
     lett
    -0.66
    ŀ
    -0.61
     traged
    -0.60
     ende
    -0.58
    STER
    -0.58
    CHA
    -0.57
     contag
    -0.56
    POSITIVE LOGITS
    ordinate
    1.24
    humane
    1.07
     vitro
    1.04
     lieu
    1.04
    operative
    1.02
    clusions
    1.01
    escap
    1.01
    sole
    0.98
    organic
    0.97
    animate
    0.96
    Activations Density 0.335%

    No Known Activations