INDEX

Explanations

phrases related to being in a particular location or state

oai_token-act-pair · gpt-3.5-turbo

the preposition "in" within various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

NOW

-0.73

 alloc

-0.68

 convol

-0.63

 arises

-0.62

irl

-0.62

uces

-0.61

Includes

-0.60

 combatants

-0.60

 notwithstanding

-0.59

 includ

-0.59

POSITIVE LOGITS

escap

1.12

ordinate

1.12

operative

1.09

bred

1.08

strument

1.07

offensive

1.05

animate

1.05

visible

1.05

humane

1.04

ching

1.02

Activations Density 0.167%

phrases related to being in a particular location or state

the preposition "in" within various contexts

No Comments

No Known Activations