INDEX

Explanations

proper nouns referring to specific geographical locations

oai_token-act-pair · gpt-3.5-turbo

references to geographical locations or communities with "Greater" or "Lower" in their names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ulators

-0.94

ulates

-0.91

ulating

-0.87

ulations

-0.86

ulator

-0.86

ulated

-0.82

cius

-0.82

ulation

-0.81

dates

-0.80

sters

-0.80

POSITIVE LOGITS

 Greater

0.93

 Than

0.79

 Area

0.74

 eleph

0.73

 Tire

0.73

 Regional

0.72

 Areas

0.72

 Territories

0.71

 Neigh

0.70

 Faster

0.70

Activations Density 0.013%

proper nouns referring to specific geographical locations

references to geographical locations or communities with "Greater" or "Lower" in their names

No Comments

No Known Activations