INDEX

Explanations

terms related to mental health and wellness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 myſelf

-0.96

 purpoſe

-0.93

 Wink

-0.93

CreateMap

-0.91

 ſame

-0.88

ValueStyle

-0.88

 Monfieur

-0.88

 raiſ

-0.88

 Gual

-0.88

 Seville

-0.87

POSITIVE LOGITS

PerformLayout

0.96

 mental

0.78

 Mental

0.74

Reentrant

0.68

mental

0.67

 Kunt

0.65

Mental

0.65

la

0.63

BRA

0.63

0.62

Activations Density 0.242%

terms related to mental health and wellness

No Comments

No Known Activations