© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 3319
    Prev
    Next
    INDEX
    Explanations

    phrases related to justifying, proving, or supporting a position or decision

    oai_token-act-pair · gpt-3.5-turbo

    references to personal or collective defense and support for claims or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibaba
    -0.81
     CrossRef
    -0.70
    yip
    -0.70
    washer
    -0.67
    atican
    -0.67
    uzzle
    -0.66
    veyard
    -0.65
     Uriel
    -0.65
    opus
    -0.64
    Boost
    -0.62
    POSITIVE LOGITS
     innocence
    1.29
     stance
    1.26
     position
    1.21
     beliefs
    1.17
     commitment
    1.16
     own
    1.15
     neutrality
    1.14
     decision
    1.13
     convictions
    1.10
     refusal
    1.08
    Activations Density 0.206%

    No Known Activations