INDEX

Explanations

phrases related to a downward direction or position

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

ificent

-0.65

Ã«

-0.62

archives

-0.60

¶ħ

-0.60

ista

-0.59

 avail

-0.59

andum

-0.58

inen

-0.57

tein

-0.56

-0.55

POSITIVE LOGITS

graded

1.40

stairs

1.32

LOAD

1.31

grading

1.29

grades

1.10

pour

1.09

hill

1.04

 stairs

1.04

loaded

1.01

sized

0.93

Activations Density 0.404%

phrases related to a downward direction or position

No Comments

No Known Activations