INDEX

Explanations

references to acquiring or possessing knowledge

oai_token-act-pair · gpt-3.5-turbo

references to the concept of knowledge and understanding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

onies

-0.67

gm

-0.64

etheus

-0.64

coni

-0.62

issions

-0.61

interstitial

-0.60

psey

-0.59

 abrupt

-0.58

addafi

-0.58

agraph

-0.57

POSITIVE LOGITS

ledge

1.19

lege

1.10

fulness

0.89

fully

0.87

¿½

0.86

 knowledge

0.82

ably

0.80

ledged

0.78

reading

0.78

knowledge

0.78

Activations Density 0.019%

references to acquiring or possessing knowledge

references to the concept of knowledge and understanding

No Comments

No Known Activations