INDEX

Explanations

mentions of specific locations

oai_token-act-pair · gpt-3.5-turbo

sentimental expressions related to emotions

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

 tremend

-0.70

etheless

-0.61

 plantation

-0.60

 blender

-0.59

anwhile

-0.58

 devise

-0.57

 harvesting

-0.57

 convergence

-0.57

 planting

-0.56

 maximizing

-0.54

POSITIVE LOGITS

º

1.00

§

0.97

¹

0.95

ı

0.94

»

0.91

¡

0.90

ł

0.88

Ĵ

0.87

į

0.86

¬

0.86

Activations Density 0.363%

mentions of specific locations

sentimental expressions related to emotions

No Comments

No Known Activations