INDEX

Explanations

statistics and numerical information

oai_token-act-pair · gpt-3.5-turbo

statistical analysis and comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 improvised

-0.72

 evac

-0.69

 cann

-0.69

 Authorization

-0.68

lication

-0.68

mos

-0.65

 Prepar

-0.62

 Compan

-0.61

DIR

-0.61

kie

-0.61

POSITIVE LOGITS

 statistical

1.24

 statistically

1.22

 trends

1.16

 disparity

1.16

 graphs

1.15

 disparities

1.15

 skewed

1.13

Chart

1.11

 averages

1.10

 anecd

1.09

Activations Density 0.676%

statistics and numerical information

statistical analysis and comparisons

No Comments

No Known Activations