INDEX

Explanations

prepositions followed by a number, indicating a location or quantity

oai_token-act-pair · gpt-3.5-turbo

prepositions and their associations with time or location

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

respective

-0.65

 contradictory

-0.63

 accumulated

-0.63

 importantly

-0.63

odd

-0.59

 seldom

-0.59

——

-0.59

 rarely

-0.58

 selves

-0.58

information

-0.57

POSITIVE LOGITS

 Depth

0.76

 Lifetime

0.74

 Desert

0.72

 Telescope

0.71

 Birthday

0.70

AZ

0.70

 Himself

0.70

 whom

0.69

 Screw

0.69

 steroids

0.69

Activations Density 0.422%

prepositions followed by a number, indicating a location or quantity

prepositions and their associations with time or location

No Comments

No Known Activations