INDEX

Explanations

keywords related to coding headers or files, particularly those with a numerical value of 8 or 9

oai_token-act-pair · gpt-3.5-turbo

instances of the word "header" and its variants related to technical documentation or programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

VK

-0.92

avid

-0.75

axis

-0.74

ingo

-0.73

eu

-0.70

olving

-0.68

olves

-0.68

áµ

-0.66

Ba

-0.66

olve

-0.65

POSITIVE LOGITS

 headers

1.19

 header

1.03

header

0.95

headers

0.92

 Header

0.80

dress

0.76

 acknowled

0.76

 jumper

0.72

ahead

0.69

 skim

0.69

Activations Density 0.007%

keywords related to coding headers or files, particularly those with a numerical value of 8 or 9

instances of the word "header" and its variants related to technical documentation or programming contexts

No Comments

No Known Activations