© 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. 12630
    Prev
    Next
    INDEX
    Explanations

    discussions or conversations about various topics

    oai_token-act-pair · gpt-3.5-turbo

    discussions centered on various topics

    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
    rift
    -0.64
     Sabha
    -0.64
    ogn
    -0.63
     jealous
    -0.63
    athy
    -0.62
    ATH
    -0.59
     depended
    -0.58
    ------------------------
    -0.58
    Lens
    -0.58
    ammy
    -0.57
    POSITIVE LOGITS
     halfway
    0.70
     topics
    0.69
     how
    0.66
     770
    0.63
     è£ı
    0.62
    PsyNetMessage
    0.61
    gres
    0.59
    >:
    0.58
     specifics
    0.58
     juven
    0.57
    Activations Density 0.122%

    No Known Activations