INDEX

Explanations

technical terms or phrases, possibly related to technology or science

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ngth

-0.77

growth

-0.69

 limp

-0.65

grass

-0.60

cham

-0.58

weights

-0.58

 Warhammer

-0.58

 regress

-0.57

MORE

-0.57

 Rivals

-0.57

POSITIVE LOGITS

itous

1.00

iqu

0.90

ues

0.89

ote

0.89

ettes

0.88

eous

0.86

istries

0.85

iri

0.83

isition

0.82

isitions

0.82

Activations Density 0.017%

technical terms or phrases, possibly related to technology or science

No Comments

No Known Activations