INDEX

Explanations

mentions of the city "Tuzla"

oai_token-act-pair · gpt-3.5-turbo

the name "Uz" or variations thereof

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

 Siren

-0.80

ADS

-0.70

brates

-0.68

IFF

-0.66

 Yards

-0.63

 Predator

-0.63

 Clicker

-0.61

 Slater

-0.60

 plaque

-0.60

 Wooden

-0.60

POSITIVE LOGITS

hao

1.05

uz

1.01

hou

1.00

awa

0.90

ombie

0.87

insk

0.87

daq

0.83

arah

0.83

alez

0.82

unda

0.82

Activations Density 0.011%

mentions of the city "Tuzla"

the name "Uz" or variations thereof

No Comments

No Known Activations