© 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. 4-RES-JB
    11. 10075
    Prev
    Next
    INDEX
    Explanations

    terms related to physical or material properties

    oai_token-act-pair · gpt-3.5-turbo

    references to various characteristics or attributes of objects or systems

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

    No Comments

    Negative Logits
    avez
    -0.69
    icago
    -0.68
     Cron
    -0.66
    scl
    -0.65
     Twins
    -0.65
    bone
    -0.64
    sie
    -0.63
    ILLE
    -0.62
    ansen
    -0.60
    Tx
    -0.60
    POSITIVE LOGITS
     properties
    1.17
    properties
    0.96
    unctions
    0.80
     Properties
    0.79
    adata
    0.74
    iveness
    0.74
    perties
    0.69
    uations
    0.68
    chool
    0.67
    Changed
    0.67
    Activations Density 0.009%

    No Known Activations