INDEX

Explanations

references to systems or processes in the context of technology or policy updates

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

$$$$

-0.88

 inflic

-0.65

ulent

-0.64

 Amen

-0.62

xit

-0.62

 degrade

-0.59

 negoti

-0.59

exit

-0.58

rolet

-0.58

æ©

-0.58

POSITIVE LOGITS

fortunately

0.90

 unfortunately

0.87

 admittedly

0.85

 understandably

0.80

 gist

0.80

 frankly

0.76

 blog

0.75

 hopefully

0.75

 lately

0.74

 topic

0.73

Activations Density 0.470%

references to systems or processes in the context of technology or policy updates

No Comments

No Known Activations