INDEX

Explanations

keywords and parameters related to programming functions and configurations

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

Code snippets and programming-related terms

np_acts-logits-general · gemini-2.0-flash

keys followed by a colon

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

↵↵

-1.20

<eos>

-1.01

-0.99

-0.92

↵↵↵

-0.85

.;

-0.78

).

-0.78

↵

-0.78

-0.75

POSITIVE LOGITS

IUrlHelper

1.29

 itſelf

1.24

 myſelf

1.20

principalTable

1.18

 propOrder

1.15

tonode

1.15

ArgsConstructor

1.15

 للاسماء

1.14

ConstraintMaker

1.14

 resourceCulture

1.13

Activations Density 0.385%

keywords and parameters related to programming functions and configurations

Code snippets and programming-related terms

keys followed by a colon

No Comments

No Known Activations