INDEX

Explanations

keyword patterns related to computer programming, particularly involving syntax and variable manipulation

oai_token-act-pair · gpt-3.5-turbo

programming concepts and variables in code

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

soever

-0.86

ãĢĳ

-0.72

Downloadha

-0.70

":"/

-0.69

 Mehran

-0.69

abwe

-0.65

quickShipAvailable

-0.65

âĸ¬

-0.64

Reviewer

-0.63

aeda

-0.62

POSITIVE LOGITS

();

0.81

();

0.77

([

0.72

((

0.71

[];

0.71

];

0.70

ALSE

0.69

((

0.67

0.66

interpret

0.66

Activations Density 0.090%

keyword patterns related to computer programming, particularly involving syntax and variable manipulation

programming concepts and variables in code

No Comments

No Known Activations