INDEX

Explanations

direct references to or mentions of the word "it"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "call" or its variations in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ashington

-0.77

oglu

-0.70

idth

-0.69

bral

-0.66

icka

-0.66

iston

-0.64

achev

-0.63

wa

-0.62

ittal

-0.62

isphere

-0.61

POSITIVE LOGITS

"#

0.78

qu

0.78

 whatever

0.75

 bluff

0.74

 heresy

0.72

ãĢİ

0.70

 anything

0.69

 treason

0.65

Activations Density 0.063%

direct references to or mentions of the word "it"

instances of the word "call" or its variations in various contexts

No Comments

No Known Activations