INDEX

Explanations

the word "inder" followed by a number which can be 6, 7, 8, 9, or 10

oai_token-act-pair · gpt-3.5-turbo

references to specific individuals, particularly those with the suffix 'inder'

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

akening

-0.78

ourt

-0.77

atted

-0.69

 tremend

-0.67

keye

-0.67

imated

-0.66

eny

-0.64

 Bour

-0.64

ONSORED

-0.63

rium

-0.63

POSITIVE LOGITS

åĤ

1.03

gaard

0.96

inder

0.94

ANCE

0.84

ance

0.83

 Singh

0.83

backer

0.83

gart

0.78

holm

0.77

haar

0.77

Activations Density 0.059%

the word "inder" followed by a number which can be 6, 7, 8, 9, or 10

references to specific individuals, particularly those with the suffix 'inder'

No Comments

No Known Activations