INDEX

Explanations

statements and references pertaining to knowledge, awareness, and recognition

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

Follows "know" and indicates certainty or acknowledgement

np_acts-logits-general · gemini-2.0-flash

know

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

expandindo

-0.77

 <<<<<<<<<<<<<<

-0.71

XmlAccessorType

-0.69

TemporalType

-0.68

 AssemblyTitle

-0.67

WriteTagHelper

-0.66

DotNetBar

-0.66

RenderAtEndOf

-0.64

middels

-0.63

 ArrayAdapter

-0.63

POSITIVE LOGITS

how

1.01

 exactly

0.97

 full

0.91

 what

0.90

 betul

0.82

 fullt

0.81

 better

0.79

 perfectly

0.77

exactly

0.76

 darn

0.75

Activations Density 0.089%

statements and references pertaining to knowledge, awareness, and recognition

Follows "know" and indicates certainty or acknowledgement

know

No Comments

No Known Activations