INDEX

Explanations

the word 'latter' used in a comparison between two elements

oai_token-act-pair · gpt-3.5-turbo

comparisons between two entities, particularly using the terms "latter" and "former."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bows

-0.73

rawdownloadcloneembedreportprint

-0.70

jong

-0.67

tnc

-0.66

eva

-0.65

krit

-0.64

hens

-0.64

 ILCS

-0.63

obal

-0.62

Avg

-0.62

POSITIVE LOGITS

mentioned

0.95

 stages

0.94

 half

0.93

 category

0.92

 part

0.82

 scenario

0.82

worldly

0.81

two

0.80

 trope

0.80

 halves

0.79

Activations Density 0.027%

the word 'latter' used in a comparison between two elements

comparisons between two entities, particularly using the terms "latter" and "former."

No Comments

No Known Activations