INDEX

Explanations

locations or entities related to Japan

oai_token-act-pair · gpt-3.5-turbo

references to specific geographical locations and names

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

ģ«

-0.89

 referen

-0.74

 Janeiro

-0.74

Â¯

-0.73

PDATE

-0.73

IDA

-0.70

Trend

-0.70

 Azerbai

-0.69

Loading

-0.67

 Archdemon

-0.65

POSITIVE LOGITS

puff

0.89

AFB

0.87

loe

0.86

ippi

0.75

igans

0.73

hof

0.72

woods

0.71

ridge

0.70

poke

0.68

swick

0.68

Activations Density 0.331%

locations or entities related to Japan

references to specific geographical locations and names

No Comments

No Known Activations