INDEX

Explanations

terms related to job opportunities and employment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MemoryWarning

-0.76

 فريبيس

-0.67

 hini

-0.65

期刊论文

-0.62

 möge

-0.62

 popolare

-0.62

 Strö

-0.62

 Kenner

-0.61

 mergeFrom

-0.60

 Lauter

-0.60

POSITIVE LOGITS

job

0.72

site

0.71

Job

0.69

Jobs

0.69

 jobs

0.67

 Jobs

0.65

JOB

0.65

getJob

0.64

 description

0.62

 done

0.60

Activations Density 0.065%

terms related to job opportunities and employment

No Comments

No Known Activations