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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3267
    Prev
    Next
    INDEX
    Explanations

    references to the International Astronomical Union (IAU)

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations and agencies

    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
    wcsstore
    -0.86
     guiActiveUnfocused
    -0.75
     Bened
    -0.74
    stories
    -0.69
    acks
    -0.68
    things
    -0.66
    ensional
    -0.65
    detail
    -0.64
     Dragonbound
    -0.64
    itude
    -0.62
    POSITIVE LOGITS
    IA
    1.27
    BILITY
    1.23
    BLE
    1.21
    IRO
    1.01
    EA
    0.99
    VA
    0.98
    IAS
    0.97
    ACA
    0.94
    LECT
    0.93
    ULT
    0.91
    Activations Density 0.007%

    No Known Activations