INDEX

Explanations

phrases related to apologies and expressions of regret

oai_token-act-pair · gpt-3.5-turbo

expressions of apology or regret

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

kefeller

-0.82

fman

-0.80

isSpecialOrderable

-0.73

eely

-0.68

idth

-0.68

quickShipAvailable

-0.67

ibaba

-0.66

Downloadha

-0.65

ighters

-0.64

å¥³

-0.64

POSITIVE LOGITS

 inconvenience

1.02

 inconven

1.00

 unres

0.87

 saddened

0.84

 insensitive

0.82

 sorry

0.82

sorry

0.82

 mistake

0.82

 interruption

0.80

 offended

0.80

Activations Density 0.124%

phrases related to apologies and expressions of regret

expressions of apology or regret

No Comments

No Known Activations