INDEX

Explanations

the word "many" with a high activation level

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "many" 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 @ 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

agame

-0.77

UAL

-0.74

icism

-0.70

ESE

-0.69

atown

-0.68

anut

-0.67

aban

-0.65

abus

-0.64

OPE

-0.64

heed

-0.63

POSITIVE LOGITS

 facets

1.21

 thousands

1.07

 different

1.06

 times

1.05

 kinds

1.02

 aspects

1.01

 occasions

0.99

 years

0.94

 iterations

0.93

 thousand

0.93

Activations Density 0.085%

the word "many" with a high activation level

occurrences of the word "many" in various contexts

No Comments

No Known Activations