INDEX

Explanations

phrases indicating a reason or explanation

oai_token-act-pair · gpt-3.5-turbo

the repeated use of the word "that" 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 @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

mosp

-0.78

ledged

-0.71

amaru

-0.70

venants

-0.70

Domin

-0.70

println

-0.69

marks

-0.68

endas

-0.61

vez

-0.61

vir

-0.61

POSITIVE LOGITS

 reason

1.86

 purpose

1.65

 sake

1.51

 purposes

1.42

 reasons

1.33

 matter

1.17

 occasion

1.05

 Purpose

1.01

 Reason

0.99

 foreseeable

0.94

Activations Density 0.076%

phrases indicating a reason or explanation

the repeated use of the word "that" in various contexts

No Comments

No Known Activations