© 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. 18077
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer hardware and software

    oai_token-act-pair · gpt-3.5-turbo

    terms related to technology, infrastructure, and various political or geographical contexts

    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
    ccording
    -0.74
    uckland
    -0.59
    choes
    -0.58
    ãĤ·ãĥ£
    -0.57
    ibrary
    -0.57
    tymology
    -0.55
    ©¶æ
    -0.55
    ACTION
    -0.55
    gage
    -0.54
     Emblem
    -0.54
    POSITIVE LOGITS
     versa
    1.12
     alike
    1.09
     thereto
    0.93
     respectively
    0.87
     thereof
    0.85
     therein
    0.77
     equivalents
    0.77
     accordingly
    0.77
     consequ
    0.76
    cellaneous
    0.75
    Activations Density 0.533%

    No Known Activations