INDEX

Explanations

terms related to recruitment activities or processes

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

"Rec" followed by a character

np_acts-logits-general · gemini-2.0-flash

words starting with rec

np_acts-logits-general · gemini-2.5-flash-lite

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

Datuak

-0.80

 consultato

-0.75

 ExecuteAsync

-0.75

 doInBackground

-0.74

 estimés

-0.74

SpringBootTest

-0.73

WireFormatLite

-0.72

 getItemId

-0.70

FontStyle

-0.69

 MessageBoxIcon

-0.69

POSITIVE LOGITS

Rec

0.95

Rec

0.92

REC

0.89

rec

0.88

rec

0.86

REC

0.74

pec

0.66

ec

0.65

reci

0.56

pro

0.55

Activations Density 0.162%

terms related to recruitment activities or processes

"Rec" followed by a character

words starting with rec

No Comments

No Known Activations