© 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. 19522
    Prev
    Next
    INDEX
    Explanations

    terms related to machine learning and artificial intelligence

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to machine learning and artificial intelligence

    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
     Daylight
    -0.88
    swick
    -0.81
    lehem
    -0.79
     Welch
    -0.74
    ength
    -0.73
    fam
    -0.71
    endez
    -0.70
     Okin
    -0.69
    irgin
    -0.69
     Whitman
    -0.69
    POSITIVE LOGITS
     algorithms
    1.38
     algorithm
    1.10
     analytics
    1.09
     bots
    0.97
     neural
    0.96
     optimization
    0.95
     technologies
    0.95
     technology
    0.92
     architectures
    0.92
     computing
    0.89
    Activations Density 0.097%

    No Known Activations