INDEX

Explanations

mentions related to a specific topic or entity

oai_token-act-pair · gpt-3.5-turbo

repetitive references to the word "that."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ormons

-0.80

ciples

-0.76

ATURES

-0.74

asters

-0.72

brates

-0.72

rior

-0.71

Ľ

-0.70

ographed

-0.69

venants

-0.68

gur

-0.65

POSITIVE LOGITS

 pesky

1.18

 particular

1.08

 fateful

1.06

 same

0.95

 kind

0.94

cher

0.90

 elusive

0.88

 aforementioned

0.86

 sort

0.84

 awful

0.82

Activations Density 0.109%

mentions related to a specific topic or entity

repetitive references to the word "that."

No Comments

No Known Activations