INDEX

Explanations

terms related to data analysis

oai_token-act-pair · gpt-3.5-turbo

references to analysis of data or information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ardless

-0.67

 Agric

-0.66

lighting

-0.64

cil

-0.63

cot

-0.62

birth

-0.59

fire

-0.59

inal

-0.58

 Nadu

-0.57

 Constantin

-0.57

POSITIVE LOGITS

mble

0.80

eering

0.80

alyses

0.78

rador

0.77

imony

0.77

racuse

0.76

nesota

0.76

 analysis

0.75

 partName

0.73

ahead

0.70

Activations Density 0.038%

terms related to data analysis

references to analysis of data or information

No Comments

No Known Activations