INDEX

Explanations

phrases related to numerical data or measurements

oai_token-act-pair · gpt-3.5-turbo

relational phrases and contextual indicators within complex statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

DEV

-0.78

API

-0.74

ãĤ«

-0.72

èª

-0.71

ãĤ³

-0.70

Gear

-0.67

ISH

-0.67

ETA

-0.65

Loading

-0.65

ä½ľ

-0.65

POSITIVE LOGITS

three

1.16

 three

1.15

 four

1.14

two

1.14

 five

1.14

six

1.11

two

1.10

TWO

1.09

four

1.08

five

1.07

Activations Density 0.292%

phrases related to numerical data or measurements

relational phrases and contextual indicators within complex statements

No Comments

No Known Activations