© 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. 8-RES-JB
    11. 17647
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of "achievement"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the prefix "ach" in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PDATE
    -0.67
    ©¶æ
    -0.65
     withd
    -0.64
    fml
    -0.61
    ences
    -0.61
     futures
    -0.60
    drm
    -0.60
     stocking
    -0.59
    FACE
    -0.59
     rall
    -0.58
    POSITIVE LOGITS
    annel
    1.05
    idon
    1.05
    ieving
    1.03
    akra
    1.01
    auri
    0.99
    alos
    0.93
    ampions
    0.93
    ingly
    0.93
    arya
    0.92
    iev
    0.92
    Activations Density 0.050%

    No Known Activations