INDEX

Explanations

affiliation or association with different entities

oai_token-act-pair · gpt-3.5-turbo

terms related to affiliation or association with organizations or groups

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

oufl

-0.74

trap

-0.71

aqu

-0.70

chat

-0.67

secution

-0.66

Iv

-0.65

othy

-0.65

 curv

-0.64

=-=-=-=-=-=-=-=-

-0.63

vict

-0.63

POSITIVE LOGITS

hips

1.20

 affili

1.14

 affiliated

1.12

 affiliation

1.02

iliated

1.01

lia

1.00

 affiliate

0.83

 affiliates

0.81

iliate

0.74

nect

0.74

Activations Density 0.022%

affiliation or association with different entities

terms related to affiliation or association with organizations or groups

No Comments

No Known Activations