INDEX

Explanations

proper nouns starting with the letter "R"

oai_token-act-pair · gpt-3.5-turbo

words related to specific character names or roles

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

ãĤ¼ãĤ¦ãĤ¹

-0.62

 Chains

-0.60

 loophole

-0.60

Spread

-0.59

 charism

-0.58

pie

-0.57

ypes

-0.57

 needle

-0.57

 envy

-0.56

lehem

-0.56

POSITIVE LOGITS

kefeller

0.91

issance

0.79

zl

0.75

restling

0.74

Īè

0.74

earchers

0.73

eway

0.69

¿

0.69

ophone

0.69

backer

0.68

Activations Density 0.098%

proper nouns starting with the letter "R"

words related to specific character names or roles

No Comments

No Known Activations