INDEX

Explanations

terms related to positive and negative emotional states or constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/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.19.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

}{*}{}

-0.61

__*/

-0.60

ChildScrollView

-0.57

 newBuilder

-0.55

 onItemClick

-0.53

 zufolge

-0.50

tagHelperRunner

-0.48

gemaakt

-0.47

ership

-0.47

brigens

-0.46

POSITIVE LOGITS

migrationBuilder

0.86

 feedback

0.85

 vibes

0.82

 negatives

0.79

Positives

0.78

 Posi

0.78

Negatives

0.77

 Feedback

0.76

Neg

0.74

aarrggbb

0.74

Activations Density 0.255%

terms related to positive and negative emotional states or constructs

No Comments

No Known Activations