INDEX

Explanations

terms related to events and locations in a specific area

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

Downloadha

-0.68

ORTS

-0.67

 blaster

-0.63

 representation

-0.60

 stabilization

-0.60

-0.59

enhagen

-0.58

 embr

-0.57

é¾įå

-0.56

 thor

-0.55

POSITIVE LOGITS

anooga

0.78

lain

0.77

Royal

0.74

qua

0.73

Ĥ

0.72

leon

0.70

ulhu

0.70

obos

0.70

obyl

0.69

Ĥ¬

0.68

Activations Density 1.317%

terms related to events and locations in a specific area

No Comments

No Known Activations