INDEX

Explanations

references to the word "Land."

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of the word "Land" in various contexts

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

Downloadha

-0.79

vernment

-0.76

umbn

-0.74

ħĭ

-0.73

ongyang

-0.73

 sidx

-0.72

pload

-0.69

thodox

-0.68

åĳ

-0.67

aukee

-0.67

POSITIVE LOGITS

scape

1.15

lords

1.02

lord

0.99

 Rover

0.95

lander

0.87

 Land

0.86

 Acquisition

0.83

mark

0.83

Land

0.82

rait

0.81

Activations Density 0.008%

references to the word "Land."

repeated mentions of the word "Land" in various contexts

No Comments

No Known Activations