INDEX

Explanations

instances of the word "several."

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "several."

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

atum

-0.74

akings

-0.72

ola

-0.72

Reviewer

-0.70

acus

-0.69

amen

-0.67

cel

-0.66

bas

-0.66

Platform

-0.66

rollers

-0.66

POSITIVE LOGITS

 hundred

1.42

 dozen

1.40

 thousand

1.27

 times

1.03

 months

0.98

een

0.98

dozen

0.97

teenth

0.93

 thous

0.92

 weeks

0.92

Activations Density 0.034%

instances of the word "several."

occurrences of the word "several."

No Comments

No Known Activations