INDEX

Explanations

phrases indicating uncertainty or questioning circumstances

oai_token-act-pair · gpt-4o-mini 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

cation

-0.97

icism

-0.89

iliation

-0.88

leness

-0.86

terness

-0.85

obook

-0.83

rency

-0.78

oire

-0.78

rower

-0.78

culosis

-0.77

POSITIVE LOGITS

 moments

1.04

 indications

1.04

 constants

1.03

 exceptions

1.03

 truths

1.01

 reminders

0.99

 examples

0.97

 cases

0.96

 occasions

0.96

 instances

0.95

Activations Density 0.252%

phrases indicating uncertainty or questioning circumstances

No Comments

No Known Activations