INDEX

Explanations

words related to changes, modifications, or transformations

oai_token-act-pair · gpt-3.5-turbo

the word "change" 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 @ 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

-+-+

-0.76

ç«

-0.75

amina

-0.74

AFB

-0.72

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

-0.72

mination

-0.70

sonian

-0.70

APH

-0.69

vern

-0.69

PLIED

-0.68

POSITIVE LOGITS

overs

0.81

agents

0.80

ogue

0.77

ĸļ

0.76

over

0.75

xual

0.70

backs

0.69

atile

0.69

 wrought

0.68

imedia

0.68

Activations Density 0.039%

words related to changes, modifications, or transformations

the word "change" in various contexts

No Comments

No Known Activations