INDEX

Explanations

specific geographic and local references, as well as words related to geographical locations and contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 itſelf

-0.78

 Diſ

-0.78

antMatchers

-0.77

 Reſ

-0.76

 pngtree

-0.74

 kasarigan

-0.74

protoimpl

-0.73

 Inſ

-0.72

 initComponents

-0.71

 Beſ

-0.71

POSITIVE LOGITS

ApiRequest

0.51

芽

0.48

Hay

0.46

ThroughAttribute

0.44

loader

0.43

再

0.43

hay

0.42

“

0.41

buttonBar

0.41

Activations Density 0.988%

specific geographic and local references, as well as words related to geographical locations and contexts

No Comments

No Known Activations