INDEX

Explanations

phrases indicating obstacles or difficulties in accessing resources or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 <=",

-0.72

poptosis

-0.72

 Generales

-0.70

 ModelExpression

-0.70

eningrad

-0.68

httphttps

-0.67

 sqft

-0.67

deceased

-0.67

 autorytatywna

-0.67

knapp

-0.65

POSITIVE LOGITS

 barriers

1.40

 barrier

1.38

 Barriers

1.20

Barriers

1.18

 obstacle

1.17

 Barrier

1.16

 opportunities

1.14

 obstacles

1.14

Barrier

1.09

barrier

1.09

Activations Density 0.057%

phrases indicating obstacles or difficulties in accessing resources or services

No Comments

No Known Activations