© 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. 2-RES-JB
    11. 12469
    Prev
    Next
    INDEX
    Explanations

    mentions of the abbreviation "sy" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    the prefix "sy" which is indicative of terms related to physical conditions or syndromes

    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
    DERR
    -0.84
    ORED
    -0.81
     actionGroup
    -0.79
    éĹĺ
    -0.73
    FM
    -0.70
    âĵĺ
    -0.67
     Bei
    -0.67
    Reviewer
    -0.66
    اÙĦ
    -0.66
    naire
    -0.65
    POSITIVE LOGITS
     sy
    1.18
    philis
    1.17
    ringe
    1.07
    seys
    0.94
    racuse
    0.93
    heter
    0.87
    lves
    0.85
    posium
    0.85
    phthal
    0.84
    rene
    0.84
    Activations Density 0.008%

    No Known Activations