INDEX

Explanations

occurrences of the word "plain" within the text

oai_token-act-pair · gpt-3.5-turbo

instances of the word "plain" 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 @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Ascend

-0.81

orsi

-0.75

 destro

-0.73

interstitial

-0.72

otos

-0.72

ulic

-0.68

orea

-0.68

orous

-0.68

etheus

-0.68

ornia

-0.66

POSITIVE LOGITS

text

1.20

cloth

0.98

 vanilla

0.95

cl

0.95

plain

0.94

rolled

0.93

ol

0.93

sheets

0.92

sheet

0.88

wallet

0.84

Activations Density 0.030%

occurrences of the word "plain" within the text

instances of the word "plain" in various contexts

No Comments

No Known Activations