INDEX

Explanations

proper nouns related to various entities and people

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

arial

-0.71

)=(

-0.68

ional

-0.66

hy

-0.66

è¡

-0.63

DERR

-0.61

lisher

-0.61

hist

-0.61

otaur

-0.61

soDeliveryDate

-0.60

POSITIVE LOGITS

 citiz

0.72

ACTED

0.65

izont

0.64

vation

0.64

+.

0.61

ecause

0.60

 cheated

0.59

caster

0.59

Reviewer

0.59

Os

0.59

Activations Density 0.571%

proper nouns related to various entities and people

proper nouns, particularly names and entities

No Comments

No Known Activations