INDEX

Explanations

phrases starting with "in light of" and followed by a noun or adjective

oai_token-act-pair · gpt-3.5-turbo

the phrase "in light of" indicating causal relationships or conditions

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

entric

-0.67

erer

-0.67

orie

-0.67

arten

-0.64

quartered

-0.63

lest

-0.63

ecycle

-0.62

bag

-0.61

quarters

-0.59

oided

-0.58

POSITIVE LOGITS

 inaction

0.75

 sheer

0.73

pty

0.72

 existing

0.71

 hypot

0.70

 circumstance

0.69

 hindsight

0.67

 impending

0.66

 jurisd

0.65

 opposing

0.65

Activations Density 0.069%

phrases starting with "in light of" and followed by a noun or adjective

the phrase "in light of" indicating causal relationships or conditions

No Comments

No Known Activations