INDEX

Explanations

references to a specific term or name, the term "Horn" or its variations

oai_token-act-pair · gpt-3.5-turbo

references to locations and entities related to "Horn" or "Hornets."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

arnaev

-0.83

NCT

-0.79

FORM

-0.72

PsyNetMessage

-0.72

ASED

-0.68

ENCY

-0.65

ACT

-0.62

ULT

-0.62

 Scotia

-0.60

ULTS

-0.60

POSITIVE LOGITS

 Horn

1.08

indal

1.01

pipe

0.98

horn

0.97

atile

0.92

atility

0.92

sey

0.89

worms

0.89

buck

0.87

worm

0.85

Activations Density 0.006%

references to a specific term or name, the term "Horn" or its variations

references to locations and entities related to "Horn" or "Hornets."

No Comments

No Known Activations