INDEX

Explanations

references to adverse experiences or negative situations, particularly involving the term "hell."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

oredCriteria

-0.48

 متعلقه

-0.48

 Secondary

-0.46

 अपनी

-0.45

res

-0.44

 Milne

-0.44

レーキ

-0.43

伍

-0.43

Pigeon

-0.43

POSITIVE LOGITS

 BorderRadius

0.91

 NgModule

0.82

 hell

0.78

 iſt

0.76

Portale

0.76

 purpoſe

0.75

 ſtate

0.75

JspWriter

0.73

etheless

0.73

 Monfieur

0.72

Activations Density 2.578%

references to adverse experiences or negative situations, particularly involving the term "hell."

No Comments

No Known Activations