INDEX

Explanations

sequences of actions and events happening in a narrative

oai_token-act-pair · gpt-3.5-turbo

emotional reactions and interactions among characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 depended

-0.81

 lacked

-0.75

 amounted

-0.74

 constituted

-0.73

 mattered

-0.72

 outwe

-0.72

 existed

-0.71

 exported

-0.69

Had

-0.67

 resided

-0.66

POSITIVE LOGITS

 flashback

0.90

POV

0.88

 yells

0.86

 explodes

0.86

 exclaim

0.85

 begins

0.84

 realizes

0.83

 grabs

0.82

 begs

0.82

 breat

0.81

Activations Density 0.897%

sequences of actions and events happening in a narrative

emotional reactions and interactions among characters

No Comments

No Known Activations