INDEX

Explanations

patterns of characters that are non-English text mixed with symbols and numbers

oai_token-act-pair · gpt-3.5-turbo

characters and numerals in various languages and scripts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

haps

-0.81

matically

-0.79

ngth

-0.79

ippi

-0.77

meal

-0.74

Else

-0.73

 myster

-0.72

 Skydragon

-0.71

asus

-0.71

avers

-0.70

POSITIVE LOGITS

ÙĬ

0.88

Ñĥ

0.85

Ø¨

0.82

ãĥ¼

0.82

ÙĪ

0.81

Ø³

0.79

rican

0.78

ãĥ¥

0.78

×ľ

0.77

rique

0.77

Activations Density 0.005%

patterns of characters that are non-English text mixed with symbols and numbers

characters and numerals in various languages and scripts

No Comments

No Known Activations