INDEX

Explanations

comparisons using the word "than"

oai_token-act-pair · gpt-3.5-turbo

comparative phrases indicating a preference or a choice

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ModLoader

-0.88

 Juda

-0.75

Contract

-0.71

Winged

-0.70

enser

-0.66

Ire

-0.65

 suspic

-0.64

ilic

-0.64

lied

-0.62

 exemptions

-0.62

POSITIVE LOGITS

atos

1.13

lihood

0.94

assis

0.81

itars

0.70

 apes

0.69

 usual

0.69

acles

0.68

gins

0.68

vation

0.67

ply

0.67

Activations Density 0.039%

comparisons using the word "than"

comparative phrases indicating a preference or a choice

No Comments

No Known Activations