INDEX

Explanations

instances of specific phonetic patterns or suffixes in words

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

 nomine

-0.61

 racks

-0.60

 Rampage

-0.59

 cater

-0.58

 legions

-0.57

 Catalyst

-0.56

ModLoader

-0.56

 Payton

-0.55

 mistress

-0.55

 Cosmos

-0.54

POSITIVE LOGITS

ublic

1.04

itone

0.86

iphany

0.85

olla

0.84

rint

0.84

ida

0.84

igen

0.83

ilon

0.82

idity

0.82

areth

0.81

Activations Density 0.004%

instances of specific phonetic patterns or suffixes in words

No Comments

No Known Activations