© 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. 6-RES-JB
    11. 1681
    Prev
    Next
    INDEX
    Explanations

    words related to specific objects, such as 'car', 'bike', 'beer', 'phone', 'device', and 'card'

    oai_token-act-pair · gpt-3.5-turbo

    common objects or items, particularly vehicles and electronic devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dhabi
    -0.80
    amy
    -0.72
    ync
    -0.69
    imon
    -0.69
    20439
    -0.67
    azeera
    -0.65
    cffff
    -0.64
    Enlarge
    -0.63
    Ĥ¬
    -0.62
    ara
    -0.61
    POSITIVE LOGITS
     itself
    0.99
     underwent
    0.90
     belonged
    0.86
    wright
    0.83
     manufact
    0.75
    maker
    0.73
     premiered
    0.73
     revolves
    0.73
     resided
    0.72
     owner
    0.72
    Activations Density 0.391%

    No Known Activations