© 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. 11-RES-JB
    11. 611
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal issues and safety concerns

    oai_token-act-pair · gpt-3.5-turbo

    punctuated phrases indicating lists or multiple ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ophon
    -0.76
    abouts
    -0.74
    ibility
    -0.72
    Orig
    -0.72
    imb
    -0.67
    utral
    -0.66
    DX
    -0.66
    é¾
    -0.65
    Availability
    -0.64
    MQ
    -0.63
    POSITIVE LOGITS
     lest
    1.17
     forgetting
    1.00
     eh
    0.98
     thereby
    0.94
     huh
    0.93
     or
    0.92
     ruining
    0.92
     ignoring
    0.89
     knowing
    0.88
     ignores
    0.88
    Activations Density 0.419%

    No Known Activations