INDEX

Explanations

instances where the word 'a' is used with a high emphasis or presence

oai_token-act-pair · gpt-3.5-turbo

instances of the article "a."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Links

-0.67

unknown

-0.66

almost

-0.65

 Loans

-0.62

Types

-0.61

scenes

-0.61

parts

-0.60

CHO

-0.60

DEF

-0.60

AUD

-0.59

POSITIVE LOGITS

 dime

1.18

 satisfactory

1.09

 coherent

1.05

 meaningful

1.04

 single

1.03

 cohesive

1.02

 proper

1.01

 slightest

0.98

rouse

0.98

lot

0.97

Activations Density 0.204%

instances where the word 'a' is used with a high emphasis or presence

instances of the article "a."

No Comments

No Known Activations