INDEX

Explanations

specific terms related to technical processes or systems

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

after "data", "evidence", or a hyphen

np_acts-logits-general · gemini-2.0-flash

driven/based completions

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

TagMode

-0.56

tisseur

-0.51

\{\\

-0.51

hysema

-0.51

τουργ

-0.49

antası

-0.49

LabelTagHelper

-0.47

帖最后由

-0.46

Unfinished

-0.46

 برانيه

-0.45

POSITIVE LOGITS

based

1.57

 based

1.53

 driven

1.47

Based

1.35

driven

1.35

 Based

1.33

 BASED

1.32

BASED

1.31

 oriented

1.25

 Driven

1.18

Activations Density 1.083%

specific terms related to technical processes or systems

after "data", "evidence", or a hyphen

driven/based completions

No Comments

No Known Activations