INDEX

Explanations

phrases indicating potential outcomes or consequences

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate significant events or conditions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

emon

-0.68

ilian

-0.64

 notions

-0.62

 supposedly

-0.62

phi

-0.61

ystem

-0.61

Prop

-0.61

 allegedly

-0.59

claim

-0.59

urus

-0.59

POSITIVE LOGITS

 someday

0.93

 tomorrow

0.91

 next

0.86

 boon

0.84

 forever

0.76

morrow

0.76

0.75

 beneficiary

0.74

 soon

0.72

0.71

Activations Density 0.340%

phrases indicating potential outcomes or consequences

phrases that indicate significant events or conditions

No Comments

No Known Activations