INDEX

Explanations

phrases related to uncertainty or questioning

oai_token-act-pair · gpt-3.5-turbo

statements of fact or assertions about various subjects

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

—-

-0.70

—"

-0.66

 Chero

-0.63

 Seym

-0.61

 beforehand

-0.56

 Afterwards

-0.56

-"

-0.55

 traged

-0.55

 summers

-0.54

||||

-0.53

POSITIVE LOGITS

rael

1.17

 hereby

0.93

ometric

0.87

olation

0.85

Ĥİ

0.82

Ĥª

0.80

 currently

0.78

 rated

0.78

olate

0.78

othermal

0.75

Activations Density 0.283%

phrases related to uncertainty or questioning

statements of fact or assertions about various subjects

No Comments

No Known Activations