INDEX

Explanations

references to organized groups and their actions in various contexts

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

 AssemblyTitle

-0.57

BrowserModule

-0.49

zwischen

-0.49

 متعلقه

-0.48

inaires

-0.48

mp

-0.47

 sais

-0.47

︎

-0.46

TimeUnit

-0.46

hian

-0.45

POSITIVE LOGITS

 group

0.97

 groups

0.96

 cohort

0.95

 cohorts

0.93

 getGroup

0.93

ArgumentParser

0.86

cohort

0.85

 flocks

0.85

 crowds

0.85

 consisting

0.85

Activations Density 0.552%

references to organized groups and their actions in various contexts

No Comments

No Known Activations