INDEX

Explanations

phrases related to various treatments and medications, particularly in the context of medical scenarios

oai_token-act-pair · gpt-3.5-turbo

occurrences of the substring "il" across various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ĪĴ

-0.81

Ħ¢

-0.81

-+-+

-0.78

reme

-0.77

©¶æ¥µ

-0.74

ĸļ

-0.74

ĵĺ

-0.74

ĳå£«

-0.73

olicy

-0.73

resy

-0.70

POSITIVE LOGITS

uvian

1.06

 Nadu

1.02

ted

1.02

aments

0.91

ogical

0.90

ibrary

0.90

uminati

0.90

ibr

0.90

iberal

0.89

ocated

0.88

Activations Density 0.047%

phrases related to various treatments and medications, particularly in the context of medical scenarios

occurrences of the substring "il" across various contexts

No Comments

No Known Activations