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

    Neuronpedia

    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. 4-RES-JB
    11. 11215
    Prev
    Next
    INDEX
    Explanations

    phrases related to academic disciplines or specific fields of study

    oai_token-act-pair · gpt-3.5-turbo

    references to biological sciences

    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
    à¨
    -0.83
    ı
    -0.79
    à©
    -0.79
    rying
    -0.71
    lished
    -0.66
    thing
    -0.65
    OWS
    -0.63
     pains
    -0.63
    rences
    -0.61
     quarters
    -0.60
    POSITIVE LOGITS
    aurus
    1.16
    clerosis
    0.99
    ophical
    0.98
    ystem
    0.94
    omething
    0.94
    anchez
    0.89
    erver
    0.87
    pell
    0.87
    perm
    0.86
    daq
    0.86
    Activations Density 0.013%

    No Known Activations