INDEX

Explanations

features or functionalities that are built-in or inherent in devices or systems

oai_token-act-pair · gpt-3.5-turbo

terms related to built-in features or components in products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ĸļ

-0.96

anches

-0.83

pid

-0.81

Ń·

-0.79

âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ

-0.76

kk

-0.76

bite

-0.75

ģ«

-0.74

Mub

-0.73

ÄŁ

-0.72

POSITIVE LOGITS

upd

0.75

 extras

0.75

 complication

0.74

 functionality

0.73

 support

0.73

 mechanism

0.72

 accessibility

0.72

 audience

0.70

omn

0.70

 error

0.70

Activations Density 0.034%

features or functionalities that are built-in or inherent in devices or systems

terms related to built-in features or components in products

No Comments

No Known Activations