INDEX

Explanations

references to minimum standards or requirements

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

什么呢

-0.44

ientras

-0.42

cinhas

-0.41

 Comprometido

-0.40

ígen

-0.39

 risa

-0.38

 informée

-0.38

 isolada

-0.37

críbete

-0.37

 aliento

-0.36

POSITIVE LOGITS

 minimum

1.27

minimum

1.10

 Minimum

1.07

Minimum

1.03

 terminal

1.01

 Terminal

0.96

 MINIMUM

0.94

Terminal

0.93

terminal

0.81

MINIMUM

0.80

Activations Density 0.234%

references to minimum standards or requirements

No Known Activations