INDEX

Explanations

statements expressing opinions or thoughts

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

uador

-0.72

ptives

-0.65

FTWARE

-0.63

avascript

-0.62

estern

-0.60

equality

-0.59

ITIES

-0.58

ensions

-0.57

prus

-0.57

anwhile

-0.56

POSITIVE LOGITS

*,

0.95

0.88

,,

0.88

!,

0.77

_.

0.74

.,

0.72

,.

0.72

 thereof

0.69

0.67

,)

0.64

Activations Density 3.121%

statements expressing opinions or thoughts

No Comments

No Known Activations