INDEX

Explanations

proper nouns and personal identifiers related to individuals' professional backgrounds

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

tagHelperRunner

-0.91

 theirs

-0.73

 MatDialog

-0.59

 ComVisible

-0.59

 '\\;'

-0.56

 proposées

-0.53

 compared

-0.52

 tampoco

-0.51

 <>",

-0.51

الحياه

-0.51

POSITIVE LOGITS

 Prior

1.10

Prior

1.09

 Previously

0.90

 Currently

0.86

Outside

0.84

Currently

0.84

Previously

0.84

 Outside

0.82

 Before

0.77

Before

0.75

Activations Density 0.178%

proper nouns and personal identifiers related to individuals' professional backgrounds

No Comments

No Known Activations