INDEX

Explanations

repeated use of the word "same" in texts

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "do the same."

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

mates

-0.72

 Provided

-0.71

 Lauder

-0.66

UST

-0.66

 Built

-0.63

mate

-0.61

 Leilan

-0.61

 Advis

-0.60

 Reborn

-0.60

Frag

-0.59

POSITIVE LOGITS

 thing

1.09

same

0.85

 vein

0.83

 amount

0.74

 exact

0.71

worldly

0.70

 happen

0.70

 deed

0.69

ials

0.68

aldi

0.68

Activations Density 0.022%

repeated use of the word "same" in texts

instances of the phrase "do the same."

No Comments

No Known Activations