INDEX

Explanations

phrases starting with "From"

oai_token-act-pair · gpt-3.5-turbo

sentences that begin with the word "From."

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

 courts

-0.65

lab

-0.64

 other

-0.62

ple

-0.62

 bench

-0.61

 care

-0.60

 duty

-0.60

 clut

-0.60

 special

-0.59

du

-0.58

POSITIVE LOGITS

From

3.09

 From

1.91

from

1.80

Between

1.72

 FROM

1.52

Through

1.48

To

1.46

With

1.45

By

1.45

Originally

1.41

Activations Density 0.010%

phrases starting with "From"

sentences that begin with the word "From."

No Comments

No Known Activations