© 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. 1-RES-JB
    11. 10457
    Prev
    Next
    INDEX
    Explanations

    words related to structured processes or systems

    oai_token-act-pair · gpt-3.5-turbo

    references to organized systems or structures in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    flies
    -0.77
     Yel
    -0.76
    nea
    -0.76
    Scot
    -0.75
    ä¹
    -0.72
    bury
    -0.72
    lake
    -0.70
    士
    -0.70
    ells
    -0.67
     Dome
    -0.67
    POSITIVE LOGITS
     structured
    1.31
    escription
    0.92
     behavi
    0.89
    urally
    0.88
     mathemat
    0.88
     misunder
    0.86
     challeng
    0.85
    paren
    0.84
     princ
    0.84
     carbohyd
    0.81
    Activations Density 0.025%

    No Known Activations