© 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. 8-RES-JB
    11. 23512
    Prev
    Next
    INDEX
    Explanations

    informal phrases or expressions

    oai_token-act-pair · gpt-3.5-turbo

    nuanced phrases related to measurement and control in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pees
    -0.82
    arte
    -0.82
    actionDate
    -0.81
    Ĭ
    -0.81
    IGHTS
    -0.81
    ongs
    -0.79
    ynthesis
    -0.79
    avi
    -0.78
    gat
    -0.77
    ograms
    -0.77
    POSITIVE LOGITS
     approach
    0.83
     version
    0.81
     residential
    0.81
     multi
    0.81
     crowd
    0.81
     compliant
    0.80
     nature
    0.79
     solution
    0.79
     versions
    0.79
     successor
    0.79
    Activations Density 0.699%

    No Known Activations