INDEX

Explanations

terms related to compatibility between different devices or systems

oai_token-act-pair · gpt-3.5-turbo

terms related to compatibility 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

vae

-0.88

vern

-0.78

esta

-0.73

nutrition

-0.71

gary

-0.71

mort

-0.70

ibur

-0.70

²¾

-0.69

otonin

-0.69

ghazi

-0.68

POSITIVE LOGITS

 compatibility

0.88

atibility

0.84

ably

0.81

 Compatibility

0.80

 compatible

0.75

icut

0.74

ivity

0.74

iations

0.72

 interoper

0.72

atible

0.70

Activations Density 0.033%

terms related to compatibility between different devices or systems

terms related to compatibility in various contexts

No Comments

No Known Activations