INDEX

Explanations

references to science and scientific concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

-0.63

yto

-0.54

-0.51

is

-0.50

-0.49

 todo

-0.49

in

-0.47

par

-0.46

col

-0.45

POSITIVE LOGITS

 science

1.22

science

1.15

 SCIENCE

1.07

WithIOException

1.07

Science

1.07

 Science

1.04

cience

1.02

SCIENCE

1.02

AndEndTag

1.00

0.97

Activations Density 0.148%

references to science and scientific concepts

No Comments

No Known Activations