INDEX

Explanations

emotions and states of mind associated with reactions to events 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

 Jobs

-0.65

 Avenger

-0.65

sov

-0.62

atcher

-0.57

 Summoner

-0.57

'/

-0.57

ezvous

-0.57

 Confederacy

-0.56

rame

-0.56

Monitor

-0.56

POSITIVE LOGITS

 abandon

0.82

 srfAttach

0.79

 impunity

0.74

idious

0.72

 flick

0.71

 afore

0.71

 strokes

0.70

 intent

0.70

 flourish

0.69

 bordering

0.68

Activations Density 0.096%

emotions and states of mind associated with reactions to events or situations

No Comments

No Known Activations