INDEX

Explanations

proper nouns related to people or places

oai_token-act-pair · gpt-3.5-turbo

references to film ratings and associated terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

imar

-0.80

Mob

-0.75

appa

-0.75

Clar

-0.69

 Racing

-0.68

icro

-0.67

car

-0.67

 Mans

-0.66

atters

-0.66

Car

-0.66

POSITIVE LOGITS

PG

4.03

SG

1.57

VG

1.43

PF

1.25

CG

1.06

MG

1.04

 Nickel

1.03

VG

1.01

SG

1.01

 Patty

0.98

Activations Density 0.042%

proper nouns related to people or places

references to film ratings and associated terms

No Comments

No Known Activations