INDEX

Explanations

mentions related to road safety

oai_token-act-pair · gpt-3.5-turbo

terms related to road safety and the associated measures

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

ividual

-0.90

arians

-0.80

illian

-0.75

ority

-0.74

iaries

-0.71

enance

-0.71

 Wong

-0.70

 Hots

-0.68

yip

-0.68

ucket

-0.68

POSITIVE LOGITS

ways

1.17

blocks

1.08

trip

1.08

block

1.01

cycle

0.91

fare

0.91

side

0.91

road

0.90

 roads

0.86

docs

0.86

Activations Density 0.020%

mentions related to road safety

terms related to road safety and the associated measures

No Comments

No Known Activations