© 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. 7-RES-JB
    11. 2156
    Prev
    Next
    INDEX
    Explanations

    names of news or media organizations

    oai_token-act-pair · gpt-3.5-turbo

    specific initials or acronyms associated with various entities or events

    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
    enegger
    -1.00
    shaw
    -0.78
    ptin
    -0.69
     Notting
    -0.66
    idem
    -0.65
    rador
    -0.63
    redients
    -0.62
    ãĤ¨ãĥ«
    -0.60
    baugh
    -0.60
    ãĤ©
    -0.60
    POSITIVE LOGITS
    Vs
    0.93
    TP
    0.90
    OD
    0.85
    RP
    0.85
    OPS
    0.85
    LC
    0.85
    ZI
    0.85
    DF
    0.84
    JA
    0.84
    NP
    0.84
    Activations Density 0.096%

    No Known Activations