INDEX

Explanations

phrases related to changes or modifications

oai_token-act-pair · gpt-3.5-turbo

references to changes in opinions, conditions, and situations

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

Magikarp

-0.72

ccoli

-0.67

Pear

-0.65

Dragon

-0.65

WAR

-0.63

Grab

-0.63

aturdays

-0.63

ulhu

-0.63

ngth

-0.62

Spoiler

-0.61

POSITIVE LOGITS

 fortunes

0.84

 radically

0.77

 drastically

0.76

 dial

0.75

 tack

0.74

 habits

0.74

 tone

0.72

 priorities

0.72

 dramatically

0.71

 clocks

0.71

Activations Density 0.222%

phrases related to changes or modifications

references to changes in opinions, conditions, and situations

No Comments

No Known Activations