INDEX

Explanations

instances where the document discusses comparisons or contrasts between two entities

oai_token-act-pair · gpt-3.5-turbo

references to comparisons or relationships involving two entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

vich

-0.78

xus

-0.69

renheit

-0.69

daq

-0.69

ÃĽ

-0.68

INESS

-0.68

 Absent

-0.68

orney

-0.68

itness

-0.66

APTER

-0.65

POSITIVE LOGITS

 halves

1.23

 extremes

1.20

 sexes

1.19

 sides

1.03

 poles

0.97

 genders

0.90

 parties

0.86

 thirds

0.82

 combatants

0.81

 continents

0.81

Activations Density 0.063%

instances where the document discusses comparisons or contrasts between two entities

references to comparisons or relationships involving two entities

No Comments

No Known Activations