INDEX

Explanations

terms related to individual entities or cases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 amnesty

-0.76

UrlResolution

-0.67

resh

-0.66

cleros

-0.65

ẹo

-0.64

 scare

-0.62

Bains

-0.62

CLO

-0.60

 Wayback

-0.59

ெ

-0.59

POSITIVE LOGITS

 individual

2.06

 Individual

2.04

Individual

1.97

 INDIVIDUAL

1.95

individual

1.88

ividual

1.84

Individuals

1.68

 individuals

1.64

 individ

1.63

 Individuals

1.61

Activations Density 0.075%

terms related to individual entities or cases

No Comments

No Known Activations

terms related to individual entities or cases

No Comments

No Known Activations