© 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. 7-RES-JB
    11. 17092
    Prev
    Next
    INDEX
    Explanations

    terms related to text formatting and coding, particularly focusing on words ending in 'ator'

    oai_token-act-pair · gpt-3.5-turbo

    words related to specific roles or titles in a hierarchical context

    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
    ITNESS
    -0.75
    earchers
    -0.73
     marrow
    -0.66
    lyak
    -0.66
    printed
    -0.66
    erton
    -0.65
    ness
    -0.65
    ãĤī
    -0.64
    ordering
    -0.63
     edible
    -0.62
    POSITIVE LOGITS
    ially
    1.01
    ators
    0.96
    SHIP
    0.89
    ator
    0.88
    iola
    0.84
    hips
    0.84
    ioch
    0.83
    oldemort
    0.81
    eers
    0.81
    iate
    0.81
    Activations Density 0.047%

    No Known Activations