© 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. 7-RES-JB
    11. 23570
    Prev
    Next
    INDEX
    Explanations

    terms related to measurements, efficiency, constraints, merits, wisdom, love, belief, role, integrity, resistance, probability, expectations, emotion, chaos, predictability, and security

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to efficiency, metrics, and the assessment of value or standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sic
    -0.73
    gow
    -0.70
    arnaev
    -0.68
    cas
    -0.68
    AMA
    -0.67
    jay
    -0.66
     Tanz
    -0.65
    ahon
    -0.64
    kus
    -0.64
    thumbnails
    -0.64
    POSITIVE LOGITS
     binds
    0.85
     arises
    0.84
     affecting
    0.83
     affects
    0.78
     consists
    0.78
     lasts
    0.75
    uous
    0.74
    olver
    0.73
     satisfies
    0.73
     arising
    0.73
    Activations Density 0.477%

    No Known Activations