© 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. 8708
    Prev
    Next
    INDEX
    Explanations

    references to the name "Jobs," likely related to Steve Jobs

    oai_token-act-pair · gpt-3.5-turbo

    references to Steve Jobs

    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
    ifiers
    -0.70
    weights
    -0.69
     Georgian
    -0.68
    weight
    -0.65
     amplification
    -0.65
    ifier
    -0.64
    ÑĤ
    -0.63
     Ukrain
    -0.63
     iodine
    -0.63
     Shiv
    -0.62
    POSITIVE LOGITS
    oint
    0.89
     Simulator
    0.83
    ython
    0.82
    intosh
    0.82
    aday
    0.82
    ð
    0.80
     Jobs
    0.78
    heimer
    0.77
    ixel
    0.77
     Maker
    0.77
    Activations Density 0.029%

    No Known Activations