INDEX

Explanations

phrases mentioning the actions or opinions of people

oai_token-act-pair · gpt-3.5-turbo

repeated usage of the pronoun "they."

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

 Globe

-0.75

 Eleven

-0.74

 Kinn

-0.66

 Electrical

-0.64

 Column

-0.62

 Claire

-0.61

 Bates

-0.60

////////////////////////////////

-0.60

 Dome

-0.60

amia

-0.60

POSITIVE LOGITS

're

1.14

've

1.06

'd

1.05

selves

0.97

'll

0.95

stanbul

0.90

 encount

0.90

 could

0.85

self

0.85

 selves

0.83

Activations Density 0.160%

phrases mentioning the actions or opinions of people

repeated usage of the pronoun "they."

No Comments

No Known Activations