INDEX

Explanations

mentions of text-related functionalities and tools

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "text" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

CVE

-0.73

CVE

-0.71

^^^^

-0.66

Ã±o

-0.64

 Daughter

-0.63

 Krish

-0.62

rolet

-0.62

nd

-0.61

lein

-0.61

 Aven

-0.61

POSITIVE LOGITS

ured

1.46

area

1.23

ural

1.16

uring

1.15

uality

1.14

ures

1.13

ually

1.06

iles

1.04

ual

1.04

urized

1.02

Activations Density 0.042%

mentions of text-related functionalities and tools

occurrences of the word "text" in various contexts

No Comments

No Known Activations