INDEX

Explanations

numbers at the beginning of sentences

oai_token-act-pair · gpt-3.5-turbo

numeric values and their relationships or implications in context

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

unia

-0.76

geries

-0.72

adr

-0.67

rator

-0.62

ãĥĹ

-0.62

ãĥĵ

-0.61

ãĥ©ãĥ³

-0.61

rugged

-0.60

weapon

-0.58

apsed

-0.58

POSITIVE LOGITS

 Conversely

0.90

theless

0.88

–

0.82

 Similarly

0.81

 although

0.80

 Furthermore

0.78

 whereas

0.78

 Moreover

0.78

â

0.77

 suggesting

0.76

Activations Density 0.076%

numbers at the beginning of sentences

numeric values and their relationships or implications in context

No Comments

No Known Activations