INDEX

Explanations

keywords related to technology and tools

oai_token-act-pair · gpt-3.5-turbo

instances of the word "that."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

EMBER

-0.63

uty

-0.56

erenn

-0.53

 Corps

-0.52

polit

-0.52

 Berm

-0.51

istani

-0.51

 Defence

-0.51

 National

-0.50

 Conference

-0.50

POSITIVE LOGITS

 doesnt

0.94

 lasted

0.92

 consists

0.89

 consisted

0.88

 violates

0.87

 translates

0.86

 includes

0.85

 lasts

0.84

 contains

0.83

 resembles

0.83

Activations Density 0.081%

keywords related to technology and tools

instances of the word "that."

No Comments

No Known Activations