© 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. 10-RES-JB
    11. 11281
    Prev
    Next
    INDEX
    Explanations

    Words with the root "achieve" and variations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "achieve" and its variations related to accomplishment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PDATE
    -0.68
     rall
    -0.66
     breakthrough
    -0.66
    FACE
    -0.64
     futures
    -0.62
    ©¶æ
    -0.61
     Fiscal
    -0.60
    PLE
    -0.58
    AX
    -0.58
     circ
    -0.58
    POSITIVE LOGITS
    icago
    1.20
    arya
    1.08
    akra
    1.06
    ieving
    1.05
    apon
    1.02
    annel
    1.01
    ieve
    1.01
    auri
    1.01
    iev
    0.99
    iever
    0.98
    Activations Density 0.043%

    No Known Activations