INDEX

Explanations

phrases related to driving offenses, particularly those related to drunk driving

oai_token-act-pair · gpt-3.5-turbo

terms related to driving offenses, particularly drunk driving

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

romeda

-0.90

ellen

-0.89

ereo

-0.82

sonian

-0.77

ropolitan

-0.76

Ã¨re

-0.76

é¾įåĸļå£«

-0.76

iao

-0.76

ertain

-0.75

 Flavoring

-0.74

POSITIVE LOGITS

 driving

1.00

driving

0.93

 Driving

0.87

 simulator

0.82

 hazard

0.80

 headlights

0.79

 wheel

0.79

 drivers

0.78

 accidents

0.77

 driver

0.76

Activations Density 0.028%

phrases related to driving offenses, particularly those related to drunk driving

terms related to driving offenses, particularly drunk driving

No Comments

No Known Activations