INDEX

Explanations

terms related to friendliness and positive social interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

endpush

-0.87

ⓧ

-0.84

 uVar

-0.74

RegistryLite

-0.74

subplots

-0.73

UnsafeEnabled

-0.69

 eventdata

-0.69

 NSCoder

-0.69

 IMDG

-0.68

/***/

-0.67

POSITIVE LOGITS

 friendly

0.82

 welcoming

0.78

 friendliness

0.75

Friendly

0.74

 Friendly

0.73

 gentler

0.72

 welcome

0.71

 vriende

0.70

friendly

0.70

 gentle

0.69

Activations Density 0.159%

terms related to friendliness and positive social interactions

No Comments

No Known Activations