INDEX

Explanations

Mentions of particular brands or products

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

ences

-0.74

ENCE

-0.69

 lockout

-0.67

WARD

-0.65

PORT

-0.64

 downhill

-0.63

FORMATION

-0.63

 Civic

-0.63

GMT

-0.63

INGTON

-0.62

POSITIVE LOGITS

icago

1.24

akra

1.15

ieft

1.11

ampions

1.10

ocolate

1.09

owder

1.09

ocobo

1.09

orus

1.09

ivalry

1.08

ampion

1.08

Activations Density 1.233%

Mentions of particular brands or products

No Comments

No Known Activations