INDEX

Explanations

references to negative events or actions

oai_token-act-pair · gpt-3.5-turbo

the repeated use of the word "the" in context

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

 again

-0.78

aja

-0.73

achus

-0.71

 instead

-0.67

worn

-0.66

 whilst

-0.66

ply

-0.65

ache

-0.65

tle

-0.65

 whenever

-0.64

POSITIVE LOGITS

 aforementioned

1.22

 latter

1.20

ses

1.06

 same

1.05

 slightest

1.00

 greatest

1.00

 latest

0.99

 Clintons

0.95

 entirety

0.90

 respective

0.89

Activations Density 0.666%

references to negative events or actions

the repeated use of the word "the" in context

No Comments

No Known Activations