© 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. 2-RES-JB
    11. 24103
    Prev
    Next
    INDEX
    Explanations

    the word "fictional" and related variations

    oai_token-act-pair · gpt-3.5-turbo

    words related to different types of institutions and their functions

    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
    uden
    -0.75
    ================
    -0.73
    Blog
    -0.72
    KO
    -0.70
    RGB
    -0.68
     Blog
    -0.67
    ARDS
    -0.65
    使
    -0.64
    ALT
    -0.64
    gone
    -0.62
    POSITIVE LOGITS
    ional
    1.09
    ities
    1.01
    izational
    0.93
    ism
    0.91
    ization
    0.90
    ized
    0.88
    isations
    0.86
    ised
    0.86
    acia
    0.85
    iott
    0.85
    Activations Density 0.010%

    No Known Activations