© 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. 4510
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant or impactful events or statements

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "never" in various contexts and expressions of loss or absence

    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
    pour
    -0.75
     Tags
    -0.75
    lass
    -0.71
    ocard
    -0.70
    nah
    -0.68
     Eug
    -0.67
    SG
    -0.66
    CRIP
    -0.66
     Pieces
    -0.65
    endar
    -0.64
    POSITIVE LOGITS
    theless
    1.26
     hesitated
    0.89
     dreamed
    0.87
     heard
    0.86
    icably
    0.85
     hesitate
    0.84
     bothered
    0.83
     EVER
    0.82
     existed
    0.80
     doubted
    0.78
    Activations Density 0.031%

    No Known Activations