INDEX

Explanations

nouns and phrases related to organizational structures and roles

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

noxious

-0.63

 Anon

-0.62

RESULTS

-0.61

urther

-0.60

esson

-0.56

)]

-0.56

 Hots

-0.55

 Logged

-0.55

 Ascend

-0.54

 ______

-0.53

POSITIVE LOGITS

 mechanism

0.85

able

0.76

less

0.72

code

0.70

 mechanisms

0.69

 structure

0.66

codes

0.66

ings

0.66

fleet

0.65

aments

0.63

Activations Density 0.311%

nouns and phrases related to organizational structures and roles

No Comments

No Known Activations