INDEX

Explanations

references to estrogen receptors in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 piedi

-0.58

 McEl

-0.56

稼

-0.56

fec

-0.55

NOPQRST

-0.53

سمبر

-0.52

eachtet

-0.52

 asmen

-0.52

ρίου

-0.52

 nahilalakip

-0.51

POSITIVE LOGITS

ER

1.77

ER

1.76

ERD

1.01

ERM

0.93

 INTERESAR

0.79

tam

0.74

 Brito

0.74

Tam

0.72

ERG

0.71

EREN

0.69

Activations Density 0.105%

references to estrogen receptors in various contexts

No Comments

No Known Activations