INDEX

Explanations

phrases related to driving a vehicle

oai_token-act-pair · gpt-3.5-turbo

the verb "drive" and its various conjugations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Seym

-0.98

 Flavoring

-0.96

ertain

-0.81

reement

-0.78

eor

-0.76

ellen

-0.75

ileaks

-0.72

olith

-0.72

reements

-0.71

ereo

-0.71

POSITIVE LOGITS

bike

0.98

wheel

0.98

 driving

0.93

driving

0.90

 away

0.86

 motorcycles

0.80

whe

0.80

boats

0.79

away

0.77

 parked

0.76

Activations Density 0.027%

phrases related to driving a vehicle

the verb "drive" and its various conjugations

No Comments

No Known Activations