INDEX

Explanations

summaries and assessments of content

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

Summarizing or encapsulating statements

np_acts-logits-general · gemini-2.0-flash

summarizing or describing something well

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

ьаж

-0.72

 nahilalakip

-0.61

tonode

-0.59

 TAMBÉM

-0.59

UnknownFieldSet

-0.58

 schal

-0.57

 quæ

-0.57

ViewImports

-0.57

 surla

-0.57

 jspb

-0.56

POSITIVE LOGITS

 summed

1.47

 sums

1.37

 summarizes

1.31

 summarize

1.31

 succinctly

1.30

 encaps

1.28

 aptly

1.19

 epitom

1.18

 perfectly

1.18

 summing

1.17

Activations Density 0.318%

summaries and assessments of content

Summarizing or encapsulating statements

summarizing or describing something well

No Comments

No Known Activations