INDEX

Explanations

proper nouns, such as names of companies, organizations, and places

oai_token-act-pair · gpt-3.5-turbo

terms related to data and organizational categories

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

ä»£

-0.76

è£

-0.72

olson

-0.71

 destro

-0.64

antage

-0.63

livion

-0.61

farious

-0.61

ourke

-0.60

present

-0.59

choes

-0.59

POSITIVE LOGITS

 Transfer

0.86

 Profile

0.83

 Rates

0.80

 Selection

0.77

 Information

0.77

 Locations

0.76

 Abilities

0.76

 Components

0.76

 Reviews

0.76

 Advice

0.76

Activations Density 0.418%

proper nouns, such as names of companies, organizations, and places

terms related to data and organizational categories

No Comments

No Known Activations