INDEX

Explanations

mentions of the word "Most" followed by a statement

oai_token-act-pair · gpt-3.5-turbo

the word "Most" 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 @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

rompt

-0.73

vest

-0.73

icer

-0.71

pload

-0.69

 SECTION

-0.66

 Mellon

-0.63

pton

-0.62

multipl

-0.62

thur

-0.61

abad

-0.61

POSITIVE LOGITS

 importantly

1.16

 notably

0.85

afa

0.84

body

0.82

likely

0.81

 important

0.79

tenance

0.78

 mornings

0.76

 egreg

0.76

entimes

0.75

Activations Density 0.056%

mentions of the word "Most" followed by a statement

the word "Most" in various contexts

No Comments

No Known Activations