INDEX

Explanations

mentions of the name "Ali."

oai_token-act-pair · gpt-3.5-turbo

occurrences of the substring "ali"

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

acters

-0.84

sylvania

-0.82

oven

-0.79

lies

-0.79

olicy

-0.79

IAL

-0.77

hered

-0.76

manship

-0.75

lov

-0.75

ly

-0.75

POSITIVE LOGITS

yah

1.05

Äĩ

0.89

ensis

0.89

Ã±o

0.88

 Lama

0.84

qi

0.83

WAYS

0.79

Ã±a

0.79

Ã±

0.75

Ã«

0.72

Activations Density 0.017%

mentions of the name "Ali."

occurrences of the substring "ali"

No Comments

No Known Activations