© 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. 23517
    Prev
    Next
    INDEX
    Explanations

    keywords related to the environment, such as "environment," "environmental," and specific descriptions like "extremely repetitive and boring environment."

    oai_token-act-pair · gpt-3.5-turbo

    terms that refer to various aspects of the environment

    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
    doms
    -0.96
    sonian
    -0.88
    thood
    -0.87
    dom
    -0.87
    head
    -0.83
    mad
    -0.83
    ilts
    -0.82
    uster
    -0.82
    headed
    -0.79
    heading
    -0.78
    POSITIVE LOGITS
     conducive
    0.89
     environment
    0.89
     Environment
    0.88
    Variable
    0.88
     environments
    0.84
     variables
    0.83
     atmosp
    0.79
     variable
    0.79
    ALLY
    0.76
    eers
    0.74
    Activations Density 0.036%

    No Known Activations