© 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. 17114
    Prev
    Next
    INDEX
    Explanations

    notification or error messages

    oai_token-act-pair · gpt-3.5-turbo

    references to errors or issues in a service or system

    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
    itatively
    -0.64
    ingers
    -0.60
    olate
    -0.56
    astically
    -0.55
    aiman
    -0.55
    asonic
    -0.51
    study
    -0.51
    uries
    -0.50
    imeters
    -0.50
    amines
    -0.50
    POSITIVE LOGITS
    taboola
    0.73
    */(
    0.58
    pport
    0.55
    ascript
    0.54
    framework
    0.51
     aligned
    0.50
    ãĤ¼ãĤ¦ãĤ¹
    0.49
    Þ
    0.49
    ]."
    0.48
    displayText
    0.48
    Activations Density 0.072%

    No Known Activations