INDEX

Explanations

commands or directives related to decision-making or action

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_fs6144-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

6,144

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

 Entered

-0.72

inently

-0.64

 tongues

-0.62

hog

-0.61

Det

-0.60

 tires

-0.60

 suspects

-0.59

rules

-0.59

 Gork

-0.58

 Prot

-0.56

POSITIVE LOGITS

pez

0.98

 differently

0.84

å¥³

0.81

 administr

0.79

ãĥ¼ãĤ¯

0.78

igraph

0.78

ÄŁ

0.76

omsday

0.72

 wrong

0.71

hing

0.68

Activations Density 0.132%

commands or directives related to decision-making or action

No Comments

No Known Activations