INDEX

Explanations

references to quantities and measurements

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate a range of possibilities or limits

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

taboola

-0.72

Ö¼

-0.71

çĶŁ

-0.69

åº

-0.67

è¦

-0.65

å£«

-0.64

Reviewer

-0.63

Dro

-0.62

Words

-0.61

Tools

-0.60

POSITIVE LOGITS

0.93

0.92

 eight

0.90

0.89

0.88

0.87

Activations Density 0.048%

references to quantities and measurements

phrases that indicate a range of possibilities or limits

No Comments

No Known Activations