INDEX

Explanations

mentions of unexpected events or outcomes

oai_token-act-pair · gpt-3.5-turbo

instances of the word "surprise" and its variations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tein

-1.05

folios

-1.00

burgh

-0.82

bis

-0.78

İĭ

-0.78

ongyang

-0.75

oreal

-0.74

onica

-0.74

oran

-0.74

uel

-0.73

POSITIVE LOGITS

 surprises

0.91

 surprise

0.90

 visitor

0.83

 arrival

0.81

 guests

0.80

 absor

0.78

 factor

0.78

 twists

0.76

 birthday

0.75

 Flavoring

0.72

Activations Density 0.047%

mentions of unexpected events or outcomes

instances of the word "surprise" and its variations

No Comments

No Known Activations