INDEX

Explanations

terms related to programming states and options within a code context

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

<start_of_turn> user

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

tagHelperRunner

-0.75

MessageOf

-0.61

 ComVisible

-0.60

 NSCoder

-0.59

principalColumn

-0.59

AddTagHelper

-0.58

 tartalomajánló

-0.58

KURZBESCHREIBUNG

-0.57

 CreateTagHelper

-0.57

]")]

-0.56

POSITIVE LOGITS

tagext

0.40

BindingResult

0.37

difice

0.35

awtextra

0.35

BeginInit

0.33

 Holstein

0.33

dotta

0.32

Nm

0.32

ตัว

0.31

 accro

0.31

Activations Density 0.032%

terms related to programming states and options within a code context

<start_of_turn> user

No Comments

No Known Activations