© 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. 6-RES-JB
    11. 11715
    Prev
    Next
    INDEX
    Explanations

    words related to evaluation and judgment, such as terms related to performance, cost, policy, efficiency, accountability, fundraising, and bias

    oai_token-act-pair · gpt-3.5-turbo

    terms related to performance, accountability, and other evaluative measures in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arnaev
    -0.67
    ovie
    -0.66
    aughters
    -0.57
    ndum
    -0.56
     Logo
    -0.55
    ortium
    -0.54
    orget
    -0.54
    ERSON
    -0.54
    uscript
    -0.53
     Rasmussen
    -0.53
    POSITIVE LOGITS
     considerations
    0.77
     constraints
    0.68
    istically
    0.68
     deprivation
    0.67
     manipulation
    0.66
    illary
    0.63
     aggregation
    0.63
     cues
    0.62
    lessly
    0.62
     purposes
    0.62
    Activations Density 0.585%

    No Known Activations