INDEX

Explanations

phrases that involve two distinct entities or locations

oai_token-act-pair · gpt-3.5-turbo

references to pairs of entities or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

utory

-0.66

 quarry

-0.64

nce

-0.63

pter

-0.63

=-=-

-0.62

 Newsletter

-0.62

ogle

-0.61

pta

-0.61

lÃ©

-0.60

arah

-0.59

POSITIVE LOGITS

 sexes

1.04

 simultaneously

1.04

paces

0.99

 equally

0.95

 halves

0.88

 respectively

0.87

 alike

0.86

 concurrently

0.86

 sides

0.85

hips

0.84

Activations Density 0.189%

phrases that involve two distinct entities or locations

references to pairs of entities or groups

No Comments

No Known Activations