INDEX

Explanations

phrases related to illegal activities involving smuggling

oai_token-act-pair · gpt-3.5-turbo

terms related to smuggling activities

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

irements

-0.84

phasis

-0.80

Ħ¢

-0.75

pring

-0.74

ŃĶ

-0.74

ovember

-0.73

Ü

-0.72

ĪĴ

-0.72

ndra

-0.71

abeth

-0.70

POSITIVE LOGITS

 smuggling

1.08

 smuggled

1.04

 smugg

0.98

 smugglers

0.91

glers

0.87

 trafficking

0.85

 traffickers

0.82

wagon

0.78

ster

0.74

 transporting

0.73

Activations Density 0.020%

phrases related to illegal activities involving smuggling

terms related to smuggling activities

No Comments

No Known Activations