© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 6175
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer programming and cybersecurity

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and sentence endings

    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
     charm
    -0.63
    ersive
    -0.61
    IRO
    -0.59
    afety
    -0.59
    okia
    -0.57
    iquette
    -0.56
     scapego
    -0.55
    ISA
    -0.54
     promise
    -0.53
     blazing
    -0.52
    POSITIVE LOGITS
     Lastly
    1.04
     Finally
    0.93
     Similarly
    0.87
     Additionally
    0.81
     Conversely
    0.80
     Alternatively
    0.80
     Likewise
    0.79
    Downloadha
    0.76
    Similarly
    0.76
    ]);
    0.75
    Activations Density 1.318%

    No Known Activations