INDEX

Explanations

verbs indicating movement or change in direction

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

âĶĢâĶĢâĶĢâĶĢ

-0.77

manship

-0.70

ollar

-0.67

finished

-0.66

 conditional

-0.61

availability

-0.59

ufficient

-0.59

iqueness

-0.58

ortunate

-0.57

ointment

-0.57

POSITIVE LOGITS

 footsteps

1.06

 corridors

0.94

 treadmill

0.92

 stairs

0.91

 paths

0.90

 distances

0.88

 downhill

0.88

 procession

0.88

 winding

0.88

err

0.87

Activations Density 1.830%

verbs indicating movement or change in direction

No Comments

No Known Activations