INDEX

Explanations

words related to software or technology

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "ware" in 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

ouri

-0.70

uations

-0.68

ivas

-0.68

ulatory

-0.66

 autonom

-0.64

ARR

-0.64

ENC

-0.63

uation

-0.63

uating

-0.60

inated

-0.60

POSITIVE LOGITS

ware

1.12

housing

1.10

houses

1.07

manship

1.05

bytes

1.01

ness

0.97

house

0.95

fare

0.92

nesses

0.89

strap

0.88

Activations Density 0.027%

words related to software or technology

occurrences of the term "ware" in various contexts

No Comments

No Known Activations