INDEX

Explanations

references to periods of time, specifically durations less than a year

oai_token-act-pair · gpt-3.5-turbo

occurrences of the article 'a' or 'an'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Edit

-0.72

 Colors

-0.64

 arrangements

-0.64

!/

-0.63

âĨ

-0.63

ãĤ¿

-0.62

ãĤ¬

-0.62

ãĤ´

-0.60

oves

-0.60

 Calcul

-0.59

POSITIVE LOGITS

 dozen

1.33

 hundred

1.18

 thousand

1.13

dozen

1.06

decade

1.05

 handful

1.05

lot

0.93

 couple

0.88

rouse

0.88

few

0.87

Activations Density 0.075%

references to periods of time, specifically durations less than a year

occurrences of the article 'a' or 'an'

No Comments

No Known Activations