INDEX

Explanations

phrases related to analysis and evaluation

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

Follows question words or indicates reasoning

np_acts-logits-general · gemini-2.0-flash

sentence enders

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

httphttps

-1.02

Efq

-1.01

 raiſ

-1.01

^(@)

-0.97

 ſever

-0.96

ſelves

-0.95

MigrationBuilder

-0.95

 myſelf

-0.94

 iſt

-0.94

?>/

-0.92

POSITIVE LOGITS

1.57

1.33

1.32

1.23

1.12

0.92

."

0.86

。

0.86

.”

0.81

.,

0.80

Activations Density 0.991%

phrases related to analysis and evaluation

Follows question words or indicates reasoning

sentence enders

No Comments

No Known Activations