INDEX

Explanations

terms related to human resources and employee performance metrics

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

efit

-0.64

eed

-0.64

ed

-0.58

 cứng

-0.57

اث

-0.57

ことが

-0.56

комму

-0.55

eeded

-0.55

eos

-0.55

enance

-0.55

POSITIVE LOGITS

RRRR

0.85

er

0.77

rrr

0.67

rrrrr

0.66

0.65

rrrr

0.63

RRR

0.63

rrrrrr

0.63

 CreateTagHelper

0.61

rr

0.61

Activations Density 0.508%

terms related to human resources and employee performance metrics

No Comments

No Known Activations