INDEX

Explanations

phrases indicating a judgment or belief about a situation or scenario

oai_token-act-pair · gpt-3.5-turbo

modal verbs that indicate possibility or speculation

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

 Bots

-0.68

 Balls

-0.65

IVES

-0.64

 Chick

-0.64

Ack

-0.63

Ry

-0.61

 jams

-0.60

 Countdown

-0.60

 Berkshire

-0.59

 Staples

-0.59

POSITIVE LOGITS

nikov

0.94

£ı

0.90

elf

0.90

uden

0.85

 oneself

0.84

agine

0.83

 imagine

0.80

 visualize

0.77

htaking

0.76

hani

0.73

Activations Density 0.091%

phrases indicating a judgment or belief about a situation or scenario

modal verbs that indicate possibility or speculation

No Comments

No Known Activations