INDEX

Explanations

phrases related to the usage of different products or services

oai_token-act-pair · gpt-3.5-turbo

terms related to frequency or measurement of usage

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

inosaur

-0.76

tell

-0.71

 Barg

-0.70

sonian

-0.67

 Kore

-0.65

bitious

-0.65

rop

-0.64

hair

-0.62

meat

-0.62

abella

-0.61

POSITIVE LOGITS

 habits

0.87

ername

0.80

 usage

0.80

iences

0.78

 patterns

0.78

 misuse

0.73

 diffusion

0.68

 interfaces

0.68

atility

0.68

 proficiency

0.68

Activations Density 0.010%

phrases related to the usage of different products or services

terms related to frequency or measurement of usage

No Comments

No Known Activations