INDEX

Explanations

the word "often" in the text

oai_token-act-pair · gpt-3.5-turbo

the frequency of the word "often" in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

utenberg

-0.79

jriwal

-0.75

vich

-0.70

 Achievement

-0.69

agate

-0.69

ENE

-0.68

 Integrity

-0.68

rowth

-0.68

ulsion

-0.67

oops

-0.66

POSITIVE LOGITS

entimes

1.59

 overlooked

1.31

 times

1.16

times

1.14

 misunderstood

1.06

 mistaken

1.05

 forgotten

1.01

 referred

1.00

 mistakenly

0.98

theless

0.96

Activations Density 0.053%

the word "often" in the text

the frequency of the word "often" in different contexts

No Comments

No Known Activations