INDEX

Explanations

quotes and statements by individuals in interviews, speeches, statements, and emails

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

atics

-0.72

haven

-0.65

edia

-0.63

abiding

-0.59

 broom

-0.59

 someday

-0.59

 needs

-0.58

ont

-0.58

atus

-0.58

 calib

-0.57

POSITIVE LOGITS

 remarks

0.97

 statement

0.87

 comments

0.85

 briefing

0.84

 emailed

0.82

 announcing

0.80

 quoted

0.78

 keynote

0.77

statement

0.77

 newsp

0.76

Activations Density 2.461%

quotes and statements by individuals in interviews, speeches, statements, and emails

No Comments

No Known Activations