INDEX

Explanations

phrases indicating possibility or likelihood

oai_token-act-pair · gpt-3.5-turbo

speculative statements or expressions of possibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ament

-0.82

cies

-0.73

 Lauder

-0.73

 Constant

-0.71

 Leah

-0.67

 Palest

-0.65

shall

-0.60

oric

-0.60

rett

-0.60

cedented

-0.60

POSITIVE LOGITS

 someday

1.19

ily

1.17

haps

1.04

 feas

1.01

iest

1.00

 conce

0.98

 offend

0.95

be

0.94

 plaus

0.93

hap

0.88

Activations Density 0.053%

phrases indicating possibility or likelihood

speculative statements or expressions of possibility

No Comments

No Known Activations