INDEX

Explanations

numerical figures and measurements in scientific figures and documents

oai_token-act-pair · gpt-3.5-turbo

references to figures and data in scientific documents

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

 academy

-0.71

panic

-0.65

 nurs

-0.63

 affairs

-0.61

netflix

-0.60

orate

-0.59

 acad

-0.59

 unsuccessfully

-0.59

unia

-0.58

ecided

-0.58

POSITIVE LOGITS

 illustrates

0.90

 summarizes

0.86

 largeDownload

0.86

below

0.82

Figure

0.80

 âĩ

0.80

 below

0.77

 summar

0.77

 depicts

0.77

 compares

0.75

Activations Density 0.048%

numerical figures and measurements in scientific figures and documents

references to figures and data in scientific documents

No Comments

No Known Activations