© 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. 8-RES-JB
    11. 23384
    Prev
    Next
    INDEX
    Explanations

    phrases related to movement or traveling

    oai_token-act-pair · gpt-3.5-turbo

    the prefix "en" as it appears in various contexts

    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
    ij士
    -0.74
    ocene
    -0.66
    DragonMagazine
    -0.65
     Palmer
    -0.63
     Heights
    -0.61
    ooth
    -0.61
    ramid
    -0.61
    ageddon
    -0.60
     Pell
    -0.60
    ACY
    -0.59
    POSITIVE LOGITS
    viron
    1.43
     masse
    1.11
    semb
    1.07
    unci
    1.07
    chanted
    1.06
    igma
    1.05
    joined
    1.05
    amel
    1.05
    closed
    1.04
    forcer
    1.03
    Activations Density 0.015%

    No Known Activations