INDEX

Explanations

words starting with the prefix 'un'

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

 briefs

-0.75

OPLE

-0.74

Tut

-0.70

MX

-0.69

hetti

-0.67

anwhile

-0.66

 Madden

-0.65

 Blitz

-0.64

 Dynamics

-0.63

 Tackle

-0.61

POSITIVE LOGITS

ruly

1.22

balanced

1.22

assuming

1.20

cles

1.18

earned

1.17

ifying

1.16

ipolar

1.14

availability

1.13

readable

1.13

numbered

1.12

Activations Density 0.796%

words starting with the prefix 'un'

No Comments

No Known Activations