INDEX

Explanations

email-related terms and actions

oai_token-act-pair · gpt-3.5-turbo

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Tradition

-0.71

 Parents

-0.66

 Kendall

-0.62

 secrecy

-0.57

 lineback

-0.56

 Technique

-0.56

 Emanuel

-0.56

 Mother

-0.55

lication

-0.55

bard

-0.54

POSITIVE LOGITS

bodied

1.04

ioned

0.93

't

0.90

iary

0.74

 access

0.74

reys

0.73

 afford

0.72

ãĥĪ

0.72

ãĥģ

0.72

ny

0.72

Activations Density 0.035%

email-related terms and actions

No Known Activations