INDEX

Explanations

phrases related to providing evidence or support for claims

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

associated with providing verification

np_acts-logits-general · gemini-2.0-flash

provided evidence or proof

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

MigrationBuilder

-0.89

 INTERESAR

-0.78

 nahilalakip

-0.71

PreferredItem

-0.70

 الحره

-0.69

IntoConstraints

-0.69

 ComVisible

-0.69

DebuggerNonUser

-0.67

 HasFactory

-0.66

RenderAtEndOf

-0.65

POSITIVE LOGITS

 evidence

1.68

 proof

1.35

evidence

1.26

 EVIDENCE

1.16

Evidence

1.15

 Evidence

1.15

 strong

1.07

 convincing

1.03

proof

1.02

 PROOF

1.01

Activations Density 1.000%

phrases related to providing evidence or support for claims

associated with providing verification

provided evidence or proof

No Comments

No Known Activations