INDEX

Explanations

instances of words related to size, magnitude, or extent

oai_token-act-pair · gpt-3.5-turbo

references to the scale and magnitude of issues or phenomena

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

isse

-0.71

ategor

-0.71

ocally

-0.69

inis

-0.69

 Gleaming

-0.66

 Scenes

-0.64

igslist

-0.64

 Adults

-0.61

ilet

-0.60

iku

-0.60

POSITIVE LOGITS

 inherent

0.82

lessness

0.81

 similarities

0.78

lihood

0.78

 unfolding

0.75

 nature

0.74

iness

0.73

iest

0.73

 crunch

0.71

of

0.69

Activations Density 0.169%

instances of words related to size, magnitude, or extent

references to the scale and magnitude of issues or phenomena

No Comments

No Known Activations