INDEX

Explanations

the letter 'g'

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

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

SPONSORED

-0.63

avorite

-0.63

 tranquil

-0.62

 sclerosis

-0.62

 merry

-0.61

 repay

-0.60

 blush

-0.59

Cause

-0.59

DEBUG

-0.59

 haun

-0.58

POSITIVE LOGITS

.,

1.25

.).

0.87

.:

0.87

ross

0.83

eter

0.78

.),

0.77

raphics

0.77

emonic

0.77

aminer

0.76

.):

0.76

Activations Density 0.004%

the letter 'g'

No Comments

No Known Activations