INDEX

Explanations

phrases or words related to "taking advantage of" or "making use of"

oai_token-act-pair · gpt-3.5-turbo

the article "the" used in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

SPONSORED

-0.87

elaide

-0.77

note

-0.69

pers

-0.66

furt

-0.65

hops

-0.65

 namely

-0.64

 SetFontSize

-0.63

Ã©e

-0.62

pelled

-0.62

POSITIVE LOGITS

 proverbial

1.01

 possibility

0.96

 seriousness

0.95

 temptation

0.94

 notion

0.94

 basics

0.89

 darkest

0.88

 assumption

0.88

 slightest

0.87

 same

0.86

Activations Density 0.884%

phrases or words related to "taking advantage of" or "making use of"

the article "the" used in various contexts

No Comments

No Known Activations