INDEX

Explanations

phrases related to expectations and predictions

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

tex

-0.81

tha

-0.70

bard

-0.70

tein

-0.69

agra

-0.69

anski

-0.69

pmwiki

-0.68

worth

-0.67

\\\\\\\\\\\\\\\\

-0.67

ophone

-0.66

POSITIVE LOGITS

antly

0.78

icipated

0.69

 successors

0.68

eers

0.66

ĭ

0.65

LY

0.65

 miracles

0.64

lessly

0.63

 future

0.63

 bells

0.63

Activations Density 0.540%

phrases related to expectations and predictions

No Comments

No Known Activations