INDEX

Explanations

personal pronouns and references to individual experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 مشين

-0.94

 AssemblyTitle

-0.84

ChildScrollView

-0.80

 Monfieur

-0.72

AutoScaleMode

-0.65

σθαι

-0.65

Efq

-0.64

 Jefus

-0.63

 Ammon

-0.63

+#+#

-0.63

POSITIVE LOGITS

 számára

0.65

にとっては

0.58

にとって

0.57

而言

0.46

 trị

0.45

tre

0.45

rinology

0.45

TagHelper

0.45

 synes

0.44

来说

0.44

Activations Density 0.224%

personal pronouns and references to individual experiences

No Comments

No Known Activations