INDEX

Explanations

technical terms related to technology and online culture

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

Not in Any Lists

No Comments

Negative Logits

actor

-0.80

zag

-0.77

agents

-0.61

uden

-0.60

 agitation

-0.60

Pav

-0.58

 incons

-0.57

 illusion

-0.56

faced

-0.56

 Doct

-0.56

POSITIVE LOGITS

0.99

0.88

%"

0.85

0.83

eenth

0.80

Hz

0.79

lvl

0.78

dayName

0.78

JV

0.77

ãĤ¨ãĥ«

0.76

Activations Density 0.062%

technical terms related to technology and online culture

No Comments

No Known Activations