© 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. 9-RES-JB
    11. 15920
    Prev
    Next
    INDEX
    Explanations

    phrases related to achievements and affiliations, especially in sports and education

    oai_token-act-pair · gpt-3.5-turbo

    numerals and punctuation marks, particularly at the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     optional
    -0.81
     explan
    -0.73
    pport
    -0.72
     nodd
    -0.69
     gau
    -0.66
     consolation
    -0.65
     dynamically
    -0.65
     asymm
    -0.65
     ecosystem
    -0.64
     stamped
    -0.63
    POSITIVE LOGITS
     During
    1.38
     Afterwards
    1.37
     Later
    1.32
     His
    1.29
     He
    1.25
     Shortly
    1.24
     Eventually
    1.21
     Prior
    1.19
     Before
    1.16
     After
    1.16
    Activations Density 0.236%

    No Known Activations