INDEX

Explanations

phrases related to ambiguity or uncertainty

oai_token-act-pair · gpt-3.5-turbo

terms related to ambiguity and caution 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 @ 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

inav

-0.77

STEM

-0.76

amb

-0.72

 kindred

-0.72

Lower

-0.71

udeb

-0.68

mop

-0.67

CAST

-0.67

upp

-0.67

fam

-0.66

POSITIVE LOGITS

eers

0.78

 theorem

0.73

 syndrome

0.73

 Solitaire

0.72

 scenario

0.70

 Â®

0.69

 complication

0.68

 fallacy

0.68

 tactic

0.67

 loophole

0.67

Activations Density 0.159%

phrases related to ambiguity or uncertainty

terms related to ambiguity and caution in various contexts

No Comments

No Known Activations