INDEX

Explanations

references to the year 2020

oai_token-act-pair · gpt-3.5-turbo

references to the year 2020

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

kell

-0.81

iqu

-0.80

lua

-0.71

ongh

-0.67

imen

-0.66

iera

-0.65

sem

-0.65

hemat

-0.65

imated

-0.65

ety

-0.63

POSITIVE LOGITS

1.13

0.99

0.92

0.88

0.80

 onwards

0.79

 census

0.75

Activations Density 0.004%

references to the year 2020

references to the year 2020

No Comments

No Known Activations