INDEX

Explanations

phrases and words related to limitations or restrictions

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

"limit" or being "limited"

np_acts-logits-general · gemini-2.0-flash

limit or restriction

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 NSCoder

-0.79

ForRow

-0.70

WEBPACK

-0.67

 AssemblyCompany

-0.67

dalena

-0.65

 initComponents

-0.63

itinéraire

-0.63

 Osama

-0.62

ętr

-0.62

weta

-0.62

POSITIVE LOGITS

 limits

1.13

 limitations

1.10

 Limit

1.07

 Limits

1.05

 Limitation

1.04

limit

1.03

 limited

1.03

limits

1.02

 limitation

1.02

 limit

1.02

Activations Density 0.172%

phrases and words related to limitations or restrictions

"limit" or being "limited"

limit or restriction

No Comments

No Known Activations