© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 24071
    Prev
    Next
    INDEX
    Explanations

    phrases related to detailed textual descriptions or explanations

    oai_token-act-pair · gpt-3.5-turbo

    references to brief explanations or summaries

    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
     Gad
    -0.66
     Ashe
    -0.60
    Sem
    -0.59
     Stadium
    -0.58
    JUST
    -0.56
     Peck
    -0.56
    833
    -0.55
     Versus
    -0.54
     compared
    -0.54
     nutshell
    -0.54
    POSITIVE LOGITS
    catentry
    0.72
    alsa
    0.71
    cellaneous
    0.69
     thereto
    0.68
    elin
    0.66
    azeera
    0.66
     modifiers
    0.66
     commentary
    0.64
     usual
    0.63
    oÄŁ
    0.63
    Activations Density 0.438%

    No Known Activations