INDEX

Explanations

words related to negative consequences or actions

oai_token-act-pair · gpt-3.5-turbo

references to suicide and related themes

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ifted

-0.52

 studied

-0.51

hung

-0.48

isted

-0.42

idered

-0.42

nostic

-0.41

 achieved

-0.41

 weighed

-0.41

 tracked

-0.40

enne

-0.40

POSITIVE LOGITS

Enlarge

0.60

Â¶

0.57

 REUTERS

0.52

ãħĭãħĭ

0.50

Community

0.50

 constitu

0.49

ocobo

0.49

java

0.49

natureconservancy

0.48

 ..........

0.48

Activations Density 1.462%

words related to negative consequences or actions

references to suicide and related themes

No Known Activations