© 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. 2-RES-JB
    11. 8393
    Prev
    Next
    INDEX
    Explanations

    negative terms or critiques in the context of a review or commentary

    oai_token-act-pair · gpt-3.5-turbo

    negative descriptors related to quality or performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awei
    -0.90
     Breach
    -0.79
     Moor
    -0.78
     Harrington
    -0.71
    utterstock
    -0.67
     Buchanan
    -0.66
    versive
    -0.66
     Farrell
    -0.64
    rity
    -0.64
    reatment
    -0.64
    POSITIVE LOGITS
    bian
    0.88
    itsch
    0.85
    icans
    0.79
    daq
    0.78
     sclerosis
    0.77
    Magikarp
    0.76
    gebra
    0.73
    Args
    0.72
    eless
    0.72
    estyle
    0.71
    Activations Density 0.020%

    No Known Activations