INDEX

Explanations

phrases related to standards, qualifications, and criteria

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

eton

-0.70

arthed

-0.64

pload

-0.63

coins

-0.62

qus

-0.61

hin

-0.60

john

-0.59

icial

-0.58

duc

-0.58

 Struggle

-0.58

POSITIVE LOGITS

 expectations

1.28

 criteria

1.23

 requirements

1.20

 standards

1.07

 threshold

1.05

 criterion

1.05

 requirement

0.96

 specifications

0.96

 milestones

0.95

 goals

0.93

Activations Density 0.039%

phrases related to standards, qualifications, and criteria

No Comments

No Known Activations