INDEX

Explanations

terms related to medical conditions and research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

aarrggbb

-0.70

Personendaten

-0.60

featureID

-0.58

ArrowToggle

-0.57

ParallelGroup

-0.53

webElementXpaths

-0.53

 pinulongan

-0.52

AxisAlignment

-0.51

 Normdatei

-0.50

:✨

-0.48

POSITIVE LOGITS

es

0.87

ws

0.87

ts

0.84

cs

0.84

hs

0.83

ns

0.83

fs

0.81

rs

0.79

ks

0.79

ds

0.78

Activations Density 0.536%

terms related to medical conditions and research

No Comments

No Known Activations