INDEX

Explanations

questions ending in a question mark

oai_token-act-pair · gpt-3.5-turbo

questions or queries, especially those phrased as inquiries

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

 marsh

-0.75

 encount

-0.73

apan

-0.71

ank

-0.69

onding

-0.66

 Nadu

-0.65

 harness

-0.64

 wilderness

-0.64

 manif

-0.64

 welf

-0.63

POSITIVE LOGITS

 Nope

1.10

.?

0.97

ï¿½ï¿½ï¿½ï¿½

0.96

 Probably

0.91

utm

0.88

Nah

0.85

Yep

0.85

Huh

0.82

 Didn

0.81

 Absolutely

0.81

Activations Density 0.105%

questions ending in a question mark

questions or queries, especially those phrased as inquiries

No Comments

No Known Activations