INDEX

Explanations

phrases related to repetitive actions or follow-up events

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

Followed by a preposition

np_acts-logits-general · gemini-2.0-flash

follow up

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Scénario

-0.63

rungsseite

-0.59

getDoctrine

-0.58

Portale

-0.58

QMetaType

-0.58

BURGH

-0.57

fml

-0.56

 Winaray

-0.56

cassert

-0.54

อ้างอิง

-0.54

POSITIVE LOGITS

0.65

 offs

0.65

outs

0.64

 outs

0.62

THRO

0.60

offs

0.60

up

0.55

out

0.53

around

0.52

away

0.52

Activations Density 0.284%

phrases related to repetitive actions or follow-up events

Followed by a preposition

follow up

No Comments

No Known Activations