© 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. 3-RES-JB
    11. 23506
    Prev
    Next
    INDEX
    Explanations

    verbs that indicate appearance, actions, or states

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating something is perceived or seems a certain way

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ascript
    -0.86
    ritical
    -0.71
    mentation
    -0.70
    ionage
    -0.70
    arching
    -0.69
     ABV
    -0.67
     concess
    -0.63
    oning
    -0.63
    ashington
    -0.62
    HAEL
    -0.61
    POSITIVE LOGITS
    cheat
    0.69
    chev
    0.69
    loo
    0.69
    fy
    0.68
    ventus
    0.67
    angu
    0.67
    paren
    0.67
    ahoo
    0.67
     favorably
    0.66
    enty
    0.66
    Activations Density 0.255%

    No Known Activations