INDEX

Explanations

notable events or entities

oai_token-act-pair · gpt-3.5-turbo

instances of the word "notable" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

claimer

-0.92

©¶æ

-0.86

prep

-0.74

uddled

-0.74

imeter

-0.70

vacc

-0.70

tein

-0.67

nan

-0.65

oping

-0.65

ceans

-0.65

POSITIVE LOGITS

 landmarks

0.94

 exceptions

0.89

Notable

0.88

 exception

0.87

 notable

0.87

 milestones

0.87

 accomplishments

0.85

 noteworthy

0.82

NESS

0.80

ãĥ³

0.79

Activations Density 0.013%

notable events or entities

instances of the word "notable" in various contexts

No Comments

No Known Activations