INDEX

Explanations

emphatic phrases indicating strong belief or certainty

oai_token-act-pair · gpt-3.5-turbo

instances of emphatic expressions or claims

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Thumbnail

-0.75

ific

-0.73

dos

-0.72

ington

-0.69

yx

-0.65

levard

-0.65

rection

-0.64

 wipe

-0.64

idian

-0.63

draw

-0.62

POSITIVE LOGITS

 sincerity

0.71

utm

0.69

 prophetic

0.68

CAR

0.66

CHR

0.63

 Accountability

0.62

 miracles

0.62

CHA

0.61

 supernatural

0.60

SQL

0.59

Activations Density 0.136%

emphatic phrases indicating strong belief or certainty

instances of emphatic expressions or claims

No Comments

No Known Activations