INDEX

Explanations

instances of personal or individual experiences, particularly related to distress, health, and personal actions

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

scription

-0.72

 Cobb

-0.66

 hysteria

-0.65

hift

-0.63

 understatement

-0.63

 Answer

-0.62

 excluding

-0.61

NET

-0.61

 Doomsday

-0.61

[/

-0.61

POSITIVE LOGITS

 greeted

0.81

 reunited

0.79

met

0.78

astery

0.78

 boarded

0.77

 stayed

0.76

 befriend

0.76

 awaited

0.74

 disembark

0.74

 sheltered

0.73

Activations Density 0.101%

instances of personal or individual experiences, particularly related to distress, health, and personal actions

No Comments

No Known Activations