INDEX

Explanations

names of individuals and their associated context

oai_token-act-pair · gpt-3.5-turbo

references to Donald Trump and phrases indicating discussion or commentary

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

sov

-1.01

ottenham

-0.91

Lenin

-0.90

ourgeois

-0.86

 dwarves

-0.85

 bour

-0.84

aukee

-0.83

 dwarf

-0.83

imbabwe

-0.82

 Dwar

-0.81

POSITIVE LOGITS

 Kelly

2.02

Kelly

1.89

 Scully

1.18

 Eagles

1.13

 Kelley

1.12

 Chip

1.08

 Keane

1.06

Lee

1.03

 Fuller

1.01

 McCoy

1.00

Activations Density 0.393%

names of individuals and their associated context

references to Donald Trump and phrases indicating discussion or commentary

No Comments

No Known Activations