INDEX

Explanations

references to the brand "Gear" followed by a number associated with it

oai_token-act-pair · gpt-3.5-turbo

references to specific brands or products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

CTR

-0.92

Mub

-0.81

 Sheen

-0.69

 Quincy

-0.66

aukee

-0.65

PsyNetMessage

-0.65

 Garg

-0.63

 Mellon

-0.63

enance

-0.63

 Treaty

-0.61

POSITIVE LOGITS

box

1.09

boxes

1.02

 gear

1.01

bag

0.89

bags

0.82

 worn

0.77

gear

0.75

shift

0.75

paio

0.74

wagon

0.74

Activations Density 0.020%

references to the brand "Gear" followed by a number associated with it

references to specific brands or products

No Comments

No Known Activations