INDEX

Explanations

references to deep emotional or psychological states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 propOrder

-1.03

antMatchers

-0.95

RegistryLite

-0.92

AccessorTable

-0.91

urlpatterns

-0.89

 Roskov

-0.88

 dévelo

-0.88

djangoproject

-0.87

 يتيمه

-0.84

MessageTagHelper

-0.83

POSITIVE LOGITS

 deep

1.81

 DEEP

1.73

 Deep

1.70

Deep

1.59

deep

1.56

DEEP

1.52

 depth

1.47

 deeper

1.43

 depths

1.43

 deeply

1.40

Activations Density 0.067%

references to deep emotional or psychological states

No Comments

No Known Activations