INDEX

Explanations

phrases or sentences predicting likelihood or probability of events

oai_token-act-pair · gpt-3.5-turbo

phrases expressing probability or likelihood

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

zeb

-0.78

gian

-0.76

cies

-0.76

ights

-0.74

izes

-0.74

ciples

-0.73

oos

-0.71

inth

-0.70

aredevil

-0.70

ithing

-0.69

POSITIVE LOGITS

 exagger

0.71

 infer

0.70

 underest

0.68

NULL

0.66

 forgotten

0.66

 likely

0.66

hap

0.65

 underestimate

0.64

 going

0.63

 enough

0.62

Activations Density 0.049%

phrases or sentences predicting likelihood or probability of events

phrases expressing probability or likelihood

No Comments

No Known Activations