INDEX

Explanations

words related to automation and self-driving technology

oai_token-act-pair · gpt-3.5-turbo

terms related to autonomous vehicle technology

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

 spat

-0.69

 Appalach

-0.68

sein

-0.68

 cereal

-0.65

 kindred

-0.65

belt

-0.64

roots

-0.64

 veil

-0.63

wid

-0.63

é¾įå¥ĳå£«

-0.62

POSITIVE LOGITS

PDATE

0.98

nesota

0.82

obiles

0.77

ãĥīãĥ©

0.74

ĳå£«

0.73

UTC

0.73

 guiName

0.72

rencies

0.71

NECT

0.70

ilot

0.70

Activations Density 0.122%

words related to automation and self-driving technology

terms related to autonomous vehicle technology

No Comments

No Known Activations