INDEX

Explanations

words related to analysis, color, armor, and defense

oai_token-act-pair · gpt-3.5-turbo

words related to analysis, color, behavior, and defense

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 VIDEOS

-0.81

Shot

-0.71

thal

-0.71

eah

-0.69

externalActionCode

-0.67

OHN

-0.67

 Carlson

-0.67

 Dull

-0.67

behavior

-0.64

 Gott

-0.63

POSITIVE LOGITS

Â£

1.07

 Whilst

0.96

 analyse

0.95

uminium

0.94

 programmes

0.93

 tyre

0.90

 defences

0.90

 tyres

0.90

 Â£

0.88

 aluminium

0.87

Activations Density 0.548%

words related to analysis, color, armor, and defense

words related to analysis, color, behavior, and defense

No Comments

No Known Activations