INDEX

Explanations

phrases related to negative events or setbacks

oai_token-act-pair · gpt-3.5-turbo

instances of significant negative events or losses

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

 Sites

-0.74

soDeliveryDate

-0.74

 Deadline

-0.73

Registered

-0.71

posted

-0.71

 Places

-0.70

 Stores

-0.69

posts

-0.66

 Lies

-0.66

INTON

-0.66

POSITIVE LOGITS

 paralysis

0.94

 wrath

0.92

 trauma

0.92

 firsthand

0.88

 severe

0.88

 hardships

0.88

parable

0.88

 loss

0.87

 transformation

0.86

 debilitating

0.85

Activations Density 0.176%

phrases related to negative events or setbacks

instances of significant negative events or losses

No Comments

No Known Activations