© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 18538
    Prev
    Next
    INDEX
    Explanations

    phrases related to considering or concerning something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote considerations or perspectives on a subject

    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
     canoe
    -0.72
     flyers
    -0.70
    ammy
    -0.69
     scattering
    -0.67
     tatt
    -0.67
     takeoff
    -0.67
     shuffle
    -0.66
     brainstorm
    -0.66
     frying
    -0.65
     snowball
    -0.64
    POSITIVE LOGITS
    enance
    1.05
    ability
    0.88
    eous
    0.87
    ibility
    0.87
    ably
    0.85
    ibly
    0.84
    rity
    0.82
    ible
    0.82
    atio
    0.81
    fulness
    0.80
    Activations Density 0.015%

    No Known Activations