INDEX

Explanations

references to historical events or dates

oai_token-act-pair · gpt-3.5-turbo

phrases that emphasize the subject "it" in various contexts

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

indal

-0.70

Appearances

-0.68

 interfering

-0.66

berra

-0.64

ultan

-0.63

 Previous

-0.63

agon

-0.59

Exit

-0.59

ophobic

-0.58

 bothering

-0.58

POSITIVE LOGITS

'll

0.70

 reasoned

0.68

 lamented

0.62

 authors

0.61

 guessed

0.61

'd

0.60

lur

0.59

 must

0.58

 Bett

0.58

 Hilton

0.58

Activations Density 0.405%

references to historical events or dates

phrases that emphasize the subject "it" in various contexts

No Comments

No Known Activations