INDEX

Explanations

keywords related to forestry and woodland management

oai_token-act-pair · gpt-3.5-turbo

references to forests

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Magikarp

-0.71

HK

-0.67

soever

-0.66

Reason

-0.66

OPLE

-0.65

IU

-0.61

Extra

-0.61

DonaldTrump

-0.61

Method

-0.60

realDonaldTrump

-0.58

POSITIVE LOGITS

lands

0.92

lake

0.91

forest

0.90

bank

0.84

ãĤ¼ãĤ¦ãĤ¹

0.82

 forests

0.81

orde

0.80

 canopy

0.79

 forest

0.79

ocene

0.77

Activations Density 0.028%

keywords related to forestry and woodland management

references to forests

No Comments

No Known Activations