© 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. 0-RES-JB
    11. 16781
    Prev
    Next
    INDEX
    Explanations

    words related to large-scale projects or operations

    oai_token-act-pair · gpt-3.5-turbo

    references to large-scale activities or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fet
    -0.84
     liber
    -0.70
     custod
    -0.69
    olic
    -0.65
    Quotes
    -0.65
     guid
    -0.64
     offended
    -0.62
     Allah
    -0.62
     ob
    -0.61
     Liber
    -0.61
    POSITIVE LOGITS
    scale
    4.14
     scale
    2.45
    Scale
    2.43
     Scale
    2.11
     scales
    1.76
    cale
    1.67
    sized
    1.42
    size
    1.35
    scope
    1.19
    volume
    1.16
    Activations Density 0.014%

    No Known Activations