INDEX

Explanations

phrases related to events or actions taken place under certain conditions

oai_token-act-pair · gpt-3.5-turbo

the word "under" in various contexts, particularly relating to policies or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ument

-0.72

auga

-0.71

-0.70

aukee

-0.64

\-

-0.61

eral

-0.60

onica

-0.60

ãĤº

-0.60

 Begins

-0.59

ospace

-0.59

POSITIVE LOGITS

lining

1.06

pins

1.05

cuts

1.03

neath

1.02

lines

1.01

dogs

1.01

whelming

0.97

lie

0.97

writing

0.95

writers

0.95

Activations Density 0.053%

phrases related to events or actions taken place under certain conditions

the word "under" in various contexts, particularly relating to policies or conditions

No Comments

No Known Activations