INDEX

Explanations

references to self-awareness or self-related constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

StoryboardSegue

-1.08

 يتيمه

-1.01

DockStyle

-0.95

enumi

-0.94

OGND

-0.93

 CreateTagHelper

-0.92

 snippetHide

-0.89

XmlAccessorType

-0.87

MemoryWarning

-0.83

URLException

-0.81

POSITIVE LOGITS

 self

3.12

 Self

2.98

Self

2.89

 SELF

2.84

self

2.75

SELF

2.60

 selves

1.84

 Selbst

1.82

Selbst

1.64

自我

1.56

Activations Density 0.084%

references to self-awareness or self-related constructs

No Comments

No Known Activations