INDEX

Explanations

locations or directions within a space, particularly focusing on the area in the front

oai_token-act-pair · gpt-3.5-turbo

references to the word "front" and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

upon

-0.73

 Fail

-0.68

edIn

-0.68

_-

-0.68

avorite

-0.65

-0.64

 Parenthood

-0.63

sbm

-0.63

ensable

-0.63

gm

-0.62

POSITIVE LOGITS

most

0.99

 periphery

0.87

 courtyard

0.83

of

0.79

 thereof

0.79

 portion

0.79

 outskirts

0.78

 pedest

0.75

 peninsula

0.74

 entrance

0.74

Activations Density 0.117%

locations or directions within a space, particularly focusing on the area in the front

references to the word "front" and its variations in different contexts

No Comments

No Known Activations