INDEX

Explanations

references to specific locations or events with the word 'Rig' in them

oai_token-act-pair · gpt-3.5-turbo

references to the word "rig."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Leilan

-0.91

etheless

-0.71

Pry

-0.65

FTA

-0.64

 Virgin

-0.64

birth

-0.61

 sands

-0.60

 Nadu

-0.60

 Taiwanese

-0.60

peak

-0.60

POSITIVE LOGITS

uez

1.28

rig

1.11

gers

1.06

iosity

1.05

gling

1.04

orously

1.02

ging

0.99

uers

0.97

gment

0.93

gered

0.92

Activations Density 0.011%

references to specific locations or events with the word 'Rig' in them

references to the word "rig."

No Comments

No Known Activations