INDEX

Explanations

text related to specific characteristics or qualities

oai_token-act-pair · gpt-3.5-turbo

mention of characteristics or traits in various contexts

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

aii

-0.83

NAS

-0.73

kos

-0.72

atorial

-0.71

endar

-0.69

ILLE

-0.69

EMS

-0.68

ADS

-0.67

psc

-0.67

heed

-0.65

POSITIVE LOGITS

 characteristics

1.09

 traits

1.05

istics

0.92

 qualities

0.84

 properties

0.80

Features

0.79

ively

0.79

 attributes

0.78

 weaknesses

0.71

natureconservancy

0.71

Activations Density 0.030%

text related to specific characteristics or qualities

mention of characteristics or traits in various contexts

No Comments

No Known Activations