INDEX

Explanations

programming-related terms related to coding, functions, and file operations

oai_token-act-pair · gpt-3.5-turbo

programming-related terms and functions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

laus

-0.80

 lawy

-0.72

oths

-0.70

guyen

-0.68

aez

-0.68

doms

-0.67

atti

-0.66

ohn

-0.65

akening

-0.65

ortment

-0.63

POSITIVE LOGITS

able

0.93

ables

0.88

Transaction

0.86

ments

0.83

ABLE

0.83

()

0.82

Property

0.78

Child

0.77

MENT

0.76

ãĥ¯

0.75

Activations Density 0.145%

programming-related terms related to coding, functions, and file operations

programming-related terms and functions

No Comments

No Known Activations