INDEX

Explanations

terms related to limitations or constraints

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

 برانيه

-0.75

cemia

-0.74

Hozzáférés

-0.73

ovsk

-0.73

iverr

-0.71

tableFuture

-0.66

labus

-0.65

izeit

-0.65

buttonBar

-0.65

 bào

-0.64

POSITIVE LOGITS

 restriction

2.58

 restrictions

2.57

 Restrictions

2.44

 Restriction

2.36

 restrict

2.25

 restricted

2.24

restriction

2.15

Restrictions

2.14

restrictions

2.13

 restricting

2.10

Activations Density 0.070%

terms related to limitations or constraints

No Comments

No Known Activations