INDEX

Explanations

phrases related to legislative or governmental settings

oai_token-act-pair · gpt-3.5-turbo

instances of the word "in" across various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 therein

-0.73

 contag

-0.67

-0.61

killer

-0.60

 lodged

-0.58

ens

-0.58

$$

-0.58

 bandwagon

-0.57

tre

-0.57

pedia

-0.57

POSITIVE LOGITS

 conjunction

1.35

 lieu

1.23

 accordance

1.22

 spite

1.19

animate

1.10

clus

1.07

escap

1.06

roads

1.06

 regards

1.03

humane

1.03

Activations Density 0.228%

phrases related to legislative or governmental settings

instances of the word "in" across various contexts

No Comments

No Known Activations