INDEX

Explanations

references to depression and its related symptoms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

UnusedPrivate

-0.91

новниш

-0.90

ритори

-0.81

 tartalomajánló

-0.80

WriteTagHelper

-0.80

URLException

-0.77

 виправивши

-0.75

ScopeManager

-0.74

CloseOperation

-0.73

rungsseite

-0.72

POSITIVE LOGITS

 depression

0.78

 admiration

0.73

 admired

0.68

 possessions

0.68

 admire

0.67

depression

0.66

 praising

0.66

 praised

0.63

 Depression

0.63

 valued

0.62

Activations Density 0.064%

references to depression and its related symptoms

No Comments

No Known Activations