INDEX

Explanations

words related to natural landscapes

oai_token-act-pair · gpt-3.5-turbo

references to the concept of landscape

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

uana

-0.81

uster

-0.78

rib

-0.76

iris

-0.75

ibo

-0.75

idel

-0.75

etts

-0.74

abad

-0.74

ighters

-0.73

irl

-0.73

POSITIVE LOGITS

scape

0.99

 landscape

0.96

 Rover

0.91

ttes

0.79

 landscapes

0.77

 backdrop

0.75

 wallpaper

0.75

geist

0.74

 Photographer

0.74

naire

0.72

Activations Density 0.008%

words related to natural landscapes

references to the concept of landscape

No Comments

No Known Activations