INDEX

Explanations

abbreviations and acronyms

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-1.06

TH

-0.96

Т

-0.87

Th

-0.81

TR

-0.80

TI

-0.78

Ti

-0.76

TA

-0.76

-0.75

Te

-0.74

POSITIVE LOGITS

ting

1.22

ten

1.21

tin

1.17

tes

1.12

to

1.08

tal

1.07

ts

1.07

the

1.07

ta

1.05

tre

1.04

Activations Density 0.525%

abbreviations and acronyms

No Comments

No Known Activations