INDEX

Explanations

time-related information, particularly mentioning days, months, and years

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

hod

-0.72

arton

-0.68

ery

-0.67

pty

-0.66

enes

-0.65

tymology

-0.65

emort

-0.65

ahime

-0.64

erie

-0.64

reth

-0.63

POSITIVE LOGITS

 thereafter

1.07

 throughout

0.81

 basis

0.80

 whatsoever

0.69

ilo

0.69

 during

0.67

(~

0.66

 until

0.65

 across

0.65

[/

0.64

Activations Density 0.517%

time-related information, particularly mentioning days, months, and years

No Comments

No Known Activations