© 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. 4-RES-JB
    11. 14815
    Prev
    Next
    INDEX
    Explanations

    adjectives and verbs related to physical actions

    oai_token-act-pair · gpt-3.5-turbo

    actions related to physical manipulation or interaction

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

    No Comments

    Negative Logits
    ²¾
    -0.87
    ©¶æ
    -0.81
    Ò
    -0.78
    «ĺ
    -0.71
     paran
    -0.71
    £ı
    -0.70
    kB
    -0.70
    oi
    -0.68
     pancakes
    -0.66
    MpServer
    -0.65
    POSITIVE LOGITS
    ãĤ¯
    0.72
    wind
    0.65
    fare
    0.65
    ament
    0.60
    Effective
    0.60
    uate
    0.59
    Critical
    0.59
    awn
    0.59
    Review
    0.57
    romy
    0.57
    Activations Density 0.000%

    No Known Activations