INDEX

Explanations

comparisons related to quantity or levels of measurement

oai_token-act-pair · gpt-3.5-turbo

references to spending or expenditures, particularly in large amounts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

xtap

-0.77

Ļ½

-0.67

ode

-0.66

pload

-0.65

ovie

-0.64

Ĭ

-0.62

comings

-0.62

SS

-0.62

ĺħ

-0.61

IPS

-0.61

POSITIVE LOGITS

 than

1.49

than

1.03

 Than

1.01

HUD

0.81

 bang

0.76

ado

0.74

 expensive

0.74

 mileage

0.73

 sophisticated

0.72

 money

0.72

Activations Density 0.102%

comparisons related to quantity or levels of measurement

references to spending or expenditures, particularly in large amounts

No Comments

No Known Activations