INDEX

Explanations

terminology related to clinical and neurobiological contexts, particularly addressing depression and somatic symptoms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

SequentialGroup

-0.79

WaitGroup

-0.76

 فريبيس

-0.74

IntoConstraints

-0.74

ChildScrollView

-0.73

 المعيارى

-0.72

rungsseite

-0.71

URLException

-0.70

 بيها

-0.69

SharedDtor

-0.66

POSITIVE LOGITS

Хьажоргаш

0.53

 هيا

0.49

sidian

0.45

urally

0.44

盡

0.43

rodu

0.42

setPreferred

0.41

ệu

0.40

 रख

0.40

gni

0.39

Activations Density 0.098%

terminology related to clinical and neurobiological contexts, particularly addressing depression and somatic symptoms

No Comments

No Known Activations