© 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. 1041
    Prev
    Next
    INDEX
    Explanations

    phrases related to official representatives

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals in spokesperson roles

    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
    avery
    -0.82
    ech
    -0.77
    life
    -0.69
    aido
    -0.66
    dream
    -0.64
    imeo
    -0.64
    bows
    -0.64
    private
    -0.63
    Bay
    -0.63
    central
    -0.62
    POSITIVE LOGITS
     spokesperson
    0.90
     Steph
    0.81
     spokesman
    0.79
     warr
    0.76
     spokeswoman
    0.73
    atography
    0.73
     ambassador
    0.72
     MLA
    0.70
     envoy
    0.68
     simultane
    0.68
    Activations Density 0.012%

    No Known Activations