INDEX

Explanations

phrases indicating the presence of specific information or data

oai_token-act-pair · gpt-3.5-turbo

occurrences of the verb "to be" in various forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

uld

-0.77

ievers

-0.75

inav

-0.72

ossom

-0.71

ienced

-0.70

venge

-0.68

iating

-0.67

roid

-0.67

poke

-0.67

addons

-0.66

POSITIVE LOGITS

 fascinating

1.11

 illust

1.11

 reprinted

1.08

 headlined

1.06

 noteworthy

1.05

 illuminating

1.04

 titled

1.02

 priceless

1.01

 reproduced

1.01

 summarized

1.00

Activations Density 0.160%

phrases indicating the presence of specific information or data

occurrences of the verb "to be" in various forms

No Comments

No Known Activations