INDEX

Explanations

terms and references related to identity, roles, and specific individuals involved in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

PreferredItem

-0.83

AddTagHelper

-0.73

Personendaten

-0.73

 nahilalakip

-0.72

WithIOException

-0.70

 postIndex

-0.69

ArrowToggle

-0.68

็จ

-0.67

elemField

-0.67

исленность

-0.65

POSITIVE LOGITS

انجليز

0.62

who

0.59

们

0.59

évaluateur

0.58

 rospy

0.57

 profondità

0.57

 geweest

0.54

 mobilité

0.51

who

0.51

farwyddwr

0.50

Activations Density 0.594%

terms and references related to identity, roles, and specific individuals involved in various contexts

No Comments

No Known Activations