© 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
    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. 17189
    Prev
    Next
    INDEX
    Explanations

    words related to power, strength, and performance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to damage, power, performance, and other metrics of effectiveness in various contexts

    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
    creen
    -0.75
    ovie
    -0.69
    uthor
    -0.66
     Tale
    -0.65
     Rue
    -0.65
    igl
    -0.62
     Friendship
    -0.62
     Vote
    -0.61
     Beck
    -0.60
    ournal
    -0.59
    POSITIVE LOGITS
     compared
    0.87
     capability
    0.81
    iencies
    0.80
     efficiency
    0.79
     output
    0.77
     advantages
    0.77
     capabilities
    0.77
     advantage
    0.75
     requirements
    0.74
     destro
    0.74
    Activations Density 0.241%

    No Known Activations