INDEX

Explanations

adverbs and their variations that describe the manner of actions

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

erto

-0.77

icip

-0.76

oresc

-0.74

ordan

-0.70

ulton

-0.65

rieving

-0.64

raltar

-0.64

HAEL

-0.63

iliate

-0.63

kowski

-0.63

POSITIVE LOGITS

 expensive

0.80

 inaccurate

0.77

 close

0.76

 awful

0.75

 ugly

0.74

pes

0.73

 sized

0.73

 inept

0.72

 accurate

0.72

 cheap

0.72

Activations Density 0.041%

adverbs and their variations that describe the manner of actions

No Comments

No Known Activations