INDEX

Explanations

the word "possible" in various contexts

oai_token-act-pair · gpt-3.5-turbo

the concept of possibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

bane

-0.95

bey

-0.79

cipl

-0.75

cipline

-0.73

zac

-0.72

ien

-0.72

raining

-0.72

gar

-0.71

mens

-0.71

mot

-0.70

POSITIVE LOGITS

ities

0.73

cffffcc

0.71

alities

0.70

 Mayhem

0.67

.>>

0.63

ITIES

0.63

 exception

0.62

 Fraud

0.62

NK

0.61

 embodiments

0.61

Activations Density 0.040%

the word "possible" in various contexts

the concept of possibility

No Comments

No Known Activations