INDEX

Explanations

numerical values within a specific range along with related statistics

oai_token-act-pair · gpt-3.5-turbo

numerical data and statistical results

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

headers

-0.63

enty

-0.62

ammy

-0.61

inventoryQuantity

-0.61

ributes

-0.60

vine

-0.60

 feeds

-0.59

cious

-0.59

_-

-0.58

dule

-0.58

POSITIVE LOGITS

 âĪĴ

0.91

âĪĴ

0.86

 Â±

0.82

 âī¤

0.81

 statistically

0.79

 heterogeneity

0.78

).

0.78

 Î²

0.78

 ÃĹ

0.77

 statistical

0.77

Activations Density 0.078%

numerical values within a specific range along with related statistics

numerical data and statistical results

No Comments

No Known Activations