INDEX

Explanations

statistical terms and values associated with analysis or experimental results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 uintptr

-0.66

 оригіналу

-0.58

principalTable

-0.52

 chargés

-0.51

 חיצוניים

-0.51

ProcessEvent

-0.51

-0.50

ьогодні

-0.48

warnai

-0.47

 nonUne

-0.47

POSITIVE LOGITS

vs

0.69

 mmHg

0.67

 patients

0.66

 versus

0.65

weeks

0.64

 weeks

0.64

median

0.61

SD

0.61

 median

0.59

%;

0.58

Activations Density 3.632%

statistical terms and values associated with analysis or experimental results

No Comments

No Known Activations