INDEX

Explanations

dialogue exchanges including characters' names and actions

oai_token-act-pair · gpt-3.5-turbo

phrases that express enthusiasm or excitement

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

 batters

-0.72

 Semin

-0.71

NCT

-0.68

utm

-0.66

Posted

-0.66

 Zamb

-0.63

geoning

-0.63

 subp

-0.63

 innov

-0.62

imeo

-0.62

POSITIVE LOGITS

-"

1.35

âĢ¦"

1.11

—"

1.08

..."

1.06

ãĢı

0.98

 Mistress

0.95

 âĢ¦"

0.94

!?"

0.92

âĢ¦."

0.90

 Hogwarts

0.88

Activations Density 0.403%

dialogue exchanges including characters' names and actions

phrases that express enthusiasm or excitement

No Comments

No Known Activations