INDEX

Explanations

keywords and phrases associated with mental health conditions, specifically depression

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

KommentareTeilen

-0.62

ilst

-0.54

 jScrollPane

-0.49

AddTagHelper

-0.48

featureID

-0.48

pyplot

-0.46

writeFieldEnd

-0.45

CreateMap

-0.44

πάρχ

-0.44

sna

-0.42

POSITIVE LOGITS

 override

1.25

override

1.21

protected

1.00

Override

0.97

 protected

0.84

 Override

0.81

 Overrides

0.80

 overrides

0.79

 Protected

0.75

OVERR

0.73

Activations Density 0.063%

keywords and phrases associated with mental health conditions, specifically depression

No Comments

No Known Activations