INDEX

Explanations

references to statistical parameters or variables

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 ―――――

-1.06

 Theſe

-1.02

 iſt

-1.01

 Anſ

-1.01

 ་་

-0.98

 doubtnut

-0.96

 Beſ

-0.96

 Monfieur

-0.95

 referenties

-0.93

 ſeveral

-0.92

POSITIVE LOGITS

2.25

1.97

1.60

getN

1.42

1.32

setN

1.31

1.25

1.23

1.19

Activations Density 0.107%

references to statistical parameters or variables

No Comments

No Known Activations