INDEX

Explanations

terms related to specific geographical locations and cultural aspects

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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

ertodd

-0.82

 Qiao

-0.81

VL

-0.79

abilities

-0.74

undo

-0.73

staking

-0.72

Internal

-0.69

anwhile

-0.68

effective

-0.68

etsk

-0.68

POSITIVE LOGITS

 accents

1.09

 accent

1.09

 cuisine

1.08

 sensibilities

1.07

 folk

1.04

 style

1.02

 slang

0.99

 tradition

0.98

 folklore

0.97

 mystic

0.96

Activations Density 0.265%

terms related to specific geographical locations and cultural aspects

No Comments

No Known Activations