INDEX

Explanations

greetings or specific actions/events with a high emotional impact

oai_token-act-pair · gpt-3.5-turbo

terms related to various roles and conditions within complex scenarios

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

 channels

-0.61

 Klux

-0.58

 Machines

-0.57

 Sections

-0.56

 Scouts

-0.56

 Clubs

-0.53

renches

-0.52

apeake

-0.52

 offices

-0.51

 Traps

-0.51

POSITIVE LOGITS

 consisting

0.79

 standpoint

0.73

cko

0.67

 comprised

0.63

ifier

0.63

 akin

0.62

 resembling

0.60

 costing

0.59

 involving

0.58

 meant

0.57

Activations Density 0.702%

greetings or specific actions/events with a high emotional impact

terms related to various roles and conditions within complex scenarios

No Comments

No Known Activations