INDEX

Explanations

instances where the word "near" is used in a context indicating either closeness or approximation

oai_token-act-pair · gpt-3.5-turbo

occurrences of the phrase "near future."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ilus

-0.83

UX

-0.74

alian

-0.73

arians

-0.72

ICAN

-0.71

uese

-0.68

gae

-0.67

CDC

-0.67

YR

-0.66

 Females

-0.66

POSITIVE LOGITS

sighted

1.27

shore

0.95

 misses

0.88

entimes

0.79

ctic

0.79

 mint

0.79

 proximity

0.76

 vicinity

0.74

0.69

 enough

0.69

Activations Density 0.023%

instances where the word "near" is used in a context indicating either closeness or approximation

occurrences of the phrase "near future."

No Comments

No Known Activations