INDEX

Explanations

text related to charitable actions and offers

oai_token-act-pair · gpt-3.5-turbo

statements expressing urgency or importance regarding action or change

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 secondly

-0.67

Secondly

-0.65

minent

-0.59

 Secondly

-0.55

è£ħ

-0.54

ģĸ

-0.54

-0.53

inian

-0.52

 neighbour

-0.50

anian

-0.49

POSITIVE LOGITS

they

0.60

 they

0.59

 alike

0.55

 ones

0.53

halla

0.53

 them

0.53

glers

0.50

rises

0.49

 distortions

0.49

!).

0.49

Activations Density 1.497%

text related to charitable actions and offers

statements expressing urgency or importance regarding action or change

No Known Activations