INDEX

Explanations

negative traits or characteristics attributed to individuals or situations

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

WARN

-0.52

eatures

-0.49

 Administrative

-0.48

INFO

-0.47

ofi

-0.46

 cumulative

-0.45

 versatility

-0.43

erenn

-0.43

ANC

-0.42

imar

-0.41

POSITIVE LOGITS

 anymore

1.06

?:

1.02

.?

1.02

?",

1.00

?,

0.97

0.94

?'

0.91

???

0.87

?????

0.86

Activations Density 0.626%

negative traits or characteristics attributed to individuals or situations

No Comments

No Known Activations