INDEX

Explanations

words related to a specific term, "Eraser."

oai_token-act-pair · gpt-3.5-turbo

the frequency of the name "Er" 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

xual

-0.83

kefeller

-0.74

ership

-0.73

 Gazette

-0.72

emouth

-0.71

erness

-0.70

creen

-0.67

 Parables

-0.66

)=(

-0.65

eries

-0.64

POSITIVE LOGITS

rors

1.18

aser

1.13

asure

1.12

bil

1.07

asures

1.00

uner

0.86

ased

0.86

kson

0.85

idan

0.84

gan

0.83

Activations Density 0.019%

words related to a specific term, "Eraser."

the frequency of the name "Er" in various contexts

No Comments

No Known Activations