INDEX

Explanations

phrases related to the use of something

oai_token-act-pair · gpt-3.5-turbo

words related to the concept of usage or application 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 @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

awk

-0.79

 Guant

-0.69

SPONSORED

-0.67

 Patron

-0.67

COMPLE

-0.66

Hai

-0.65

 Fidel

-0.64

wards

-0.64

Hou

-0.62

Ń·

-0.62

POSITIVE LOGITS

 Used

0.93

 used

0.80

 reused

0.75

 condoms

0.74

Used

0.72

ãĥ¯

0.71

 sparing

0.70

nesday

0.69

fully

0.69

 aback

0.69

Activations Density 0.045%

phrases related to the use of something

words related to the concept of usage or application in various contexts

No Comments

No Known Activations