INDEX

Explanations

positive commentary and opinions

oai_token-act-pair · gpt-3.5-turbo

expressions of personal preference and emotional responses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 legisl

-0.57

 constitutional

-0.57

 unlawfully

-0.56

economic

-0.56

 elector

-0.56

 administr

-0.54

 wage

-0.54

 ministerial

-0.54

 constitutionally

-0.53

 jointly

-0.53

POSITIVE LOGITS

 Horror

0.58

 Weird

0.55

 Rebirth

0.55

Laughs

0.55

 Animation

0.55

 Hitch

0.54

 Wonderland

0.54

 Ragnarok

0.53

laughs

0.53

 Lovecraft

0.53

Activations Density 4.488%

positive commentary and opinions

expressions of personal preference and emotional responses

No Comments

No Known Activations