© 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. 2-RES-JB
    11. 4530
    Prev
    Next
    INDEX
    Explanations

    terms related to the installation and operation of a specific software system, PostgresQL

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the PostgreSQL database

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icum
    -0.69
     Sik
    -0.69
     Slater
    -0.65
     Outs
    -0.64
    rip
    -0.63
     Wink
    -0.62
     negotiators
    -0.60
    liners
    -0.59
     AAP
    -0.58
     allies
    -0.58
    POSITIVE LOGITS
    ql
    1.09
    lishing
    1.07
    gres
    1.00
    greSQL
    0.98
    asper
    0.86
    pport
    0.85
    pload
    0.83
    furt
    0.81
    asus
    0.81
    ppelin
    0.79
    Activations Density 0.027%

    No Known Activations