INDEX

Explanations

terms related to new entities, innovations, and developments

oai_token-act-pair · gpt-3.5-turbo

references to new entities, roles, or concepts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.9.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

otal

-0.70

akespeare

-0.62

SPONSORED

-0.59

anuts

-0.59

 OTHER

-0.58

ecause

-0.58

 otherwise

-0.57

vag

-0.57

ashtra

-0.57

fore

-0.56

POSITIVE LOGITS

 arrivals

1.01

 entrants

0.89

 hires

0.87

anding

0.81

 additions

0.81

 recruits

0.80

 paradigm

0.75

stadt

0.74

 hire

0.72

 technologies

0.72

Activations Density 0.458%

terms related to new entities, innovations, and developments

references to new entities, roles, or concepts

No Comments

No Known Activations