INDEX

Explanations

terms related to medical conditions or treatments

oai_token-act-pair · gpt-3.5-turbo

phrases that include the article "a."

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

assisted

-0.82

sheets

-0.73

Attempts

-0.70

OWS

-0.69

ographs

-0.67

 endeavors

-0.66

eyes

-0.65

Imagine

-0.65

anism

-0.65

measures

-0.65

POSITIVE LOGITS

lot

1.29

 plethora

1.10

 tremendous

1.06

LOT

1.00

 possibility

1.00

 huge

0.99

 bunch

0.98

 multitude

0.97

 definite

0.96

 chance

0.95

Activations Density 0.114%

terms related to medical conditions or treatments

phrases that include the article "a."

No Comments

No Known Activations