INDEX

Explanations

terms related to burning and combustion

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 EconPapers

-0.86

:+:

-0.79

 kasarigan

-0.77

principalTable

-0.75

 خارجية

-0.72

evsky

-0.71

 Fabio

-0.70

 newArray

-0.70

 câte

-0.68

 rând

-0.66

POSITIVE LOGITS

 burn

1.83

 BURN

1.81

 burns

1.81

 burning

1.74

 Burn

1.73

 Burning

1.70

 Burns

1.69

 burned

1.63

burning

1.62

Burn

1.61

Activations Density 0.085%

terms related to burning and combustion

No Comments

No Known Activations