INDEX

Explanations

references to specific individuals or entities in a narrative context

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

ãĥ£

-0.76

ablishment

-0.73

places

-0.71

ãĥ´

-0.69

charge

-0.65

 scratch

-0.64

company

-0.64

ãĥ¥

-0.64

definition

-0.63

ãĥ

-0.60

POSITIVE LOGITS

owship

1.15

sburgh

1.08

inson

0.98

0.95

ski

0.90

sburg

0.89

ateral

0.86

sie

0.85

yth

0.83

inelli

0.82

Activations Density 0.003%

references to specific individuals or entities in a narrative context

No Comments

No Known Activations