INDEX

Explanations

code-related terms and syntax

oai_token-act-pair · gpt-3.5-turbo

specific symbols or characters used in coding or programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

oted

-0.77

otion

-0.67

 Pony

-0.64

anyl

-0.63

umbn

-0.62

 menstru

-0.62

esting

-0.62

 ancest

-0.59

Peb

-0.59

 Stard

-0.59

POSITIVE LOGITS

âĤ¬

1.12

Â¢

0.92

Ã¯

0.90

hyde

0.85

Ëľ

0.84

Â£

0.84

 âĤ¬

0.80

reci

0.75

Ì¶

0.75

Ã§

0.74

Activations Density 0.004%

code-related terms and syntax

specific symbols or characters used in coding or programming contexts

No Comments

No Known Activations