© 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. 3-RES-JB
    11. 10772
    Prev
    Next
    INDEX
    Explanations

    words ending in 'ing'

    oai_token-act-pair · gpt-3.5-turbo

    words related to tense and actions

    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
    ĨĴ
    -0.79
     tremend
    -0.72
    ģĸ
    -0.67
    ĺħ
    -0.63
    ñ
    -0.62
     metic
    -0.62
    ĻĤ
    -0.62
     morphine
    -0.61
    ò
    -0.61
     carbohyd
    -0.60
    POSITIVE LOGITS
    ails
    0.76
    akeru
    0.75
    qt
    0.74
    endants
    0.74
    obl
    0.73
    ons
    0.71
    ng
    0.71
    united
    0.70
    ail
    0.70
    inki
    0.69
    Activations Density 0.122%

    No Known Activations