INDEX

Explanations

instances of the word "generally."

oai_token-act-pair · gpt-3.5-turbo

the frequency of the word "generally" in various contexts

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

planet

-0.66

ibi

-0.63

!!

-0.62

 Countdown

-0.62

ourney

-0.62

las

-0.62

ache

-0.61

izer

-0.60

!!"

-0.59

gotten

-0.58

POSITIVE LOGITS

 generally

3.30

 typically

2.09

 usually

1.99

 broadly

1.92

 Generally

1.81

Generally

1.73

 ordinarily

1.69

 often

1.65

 invariably

1.64

typically

1.64

Activations Density 0.013%

instances of the word "generally."

the frequency of the word "generally" in various contexts

No Comments

No Known Activations