INDEX

Explanations

words or phrases related to explanations or clarifications

oai_token-act-pair · gpt-3.5-turbo

instances of the word "clarify" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MET

-0.86

 Spice

-0.72

NCT

-0.70

 Derby

-0.66

CVE

-0.66

gor

-0.64

hyde

-0.62

ï¸

-0.61

FAULT

-0.61

llah

-0.60

POSITIVE LOGITS

ifications

1.62

ifying

1.43

inet

1.36

ification

1.25

ifies

1.24

ifiers

1.21

ifier

1.15

ified

1.11

ific

1.06

ities

1.06

Activations Density 0.041%

words or phrases related to explanations or clarifications

instances of the word "clarify" and its variations

No Comments

No Known Activations