INDEX

Explanations

phrases related to movement or physical proximity

oai_token-act-pair · gpt-3.5-turbo

the word "around."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

BT

-0.68

qua

-0.68

 tatt

-0.62

Wr

-0.61

idy

-0.58

BILL

-0.57

 Shock

-0.57

Pl

-0.56

 Architects

-0.56

-0.55

POSITIVE LOGITS

abouts

0.87

ciating

0.86

ouver

0.78

rocal

0.75

 corners

0.74

apons

0.72

 ..........

0.72

ruciating

0.72

atform

0.70

ento

0.68

Activations Density 0.040%

phrases related to movement or physical proximity

the word "around."

No Comments

No Known Activations