INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

variations of the letter "L" represented by the character Ļ

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 Rhodes

-0.68

 Negro

-0.66

 STATES

-0.61

 Allied

-0.60

 Royale

-0.60

 JPEG

-0.60

 Orchestra

-0.59

 Kansas

-0.57

 Newark

-0.56

 Monroe

-0.56

POSITIVE LOGITS

ï¸ı

1.47

ï¸

1.00

tracks

1.00

esc

0.94

0.90

ski

0.88

tra

0.84

tracking

0.83

track

0.83

eal

0.83

Activations Density 0.224%

proper nouns

variations of the letter "L" represented by the character Ļ

No Comments

No Known Activations