INDEX

Explanations

concepts related to mental health and its intersections with other factors

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

Follows negative sentiment words

np_acts-logits-general · gemini-2.0-flash

negative outcomes and evaluations

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/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.24.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

 peindre

-0.46

guien

-0.40

TagHelper

-0.39

 découver

-0.39

 parlé

-0.39

 déclar

-0.38

Upstairs

-0.38

umque

-0.38

letzt

-0.38

 Infórmanos

-0.38

POSITIVE LOGITS

 undesirable

1.33

 disappointment

1.32

 disappointing

1.31

 failures

1.29

 disastrous

1.28

 unpleasant

1.28

 wrong

1.28

 unsatisfactory

1.27

 failure

1.27

 incorrect

1.25

Activations Density 2.101%

concepts related to mental health and its intersections with other factors

Follows negative sentiment words

negative outcomes and evaluations

No Comments

No Known Activations