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

    Neuronpedia

    Jacobian LensNEW
    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. 6546
    Prev
    Next
    INDEX
    Explanations

    words related to consumables or consumable components

    oai_token-act-pair · gpt-3.5-turbo

    references to consumables and inconclusive concepts

    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
     Ferdinand
    -0.82
     Manz
    -0.79
    andr
    -0.70
    cliffe
    -0.68
    Joined
    -0.65
    ħĭ
    -0.65
     Leia
    -0.60
     Estimates
    -0.60
     Pyth
    -0.60
    onew
    -0.59
    POSITIVE LOGITS
    ables
    0.93
    uble
    0.89
    uity
    0.83
    ilial
    0.83
    ensation
    0.83
    able
    0.81
    alty
    0.80
    ke
    0.80
    rative
    0.79
    rament
    0.79
    Activations Density 0.021%

    No Known Activations