INDEX

Explanations

phrases and words related to email promotions

oai_token-act-pair · gpt-3.5-turbo

instances of punctuation and formatting in writing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

iter

-0.74

Foot

-0.68

rely

-0.67

ensical

-0.65

orable

-0.65

olas

-0.65

 comprom

-0.65

paces

-0.65

imus

-0.62

uder

-0.62

POSITIVE LOGITS

,,,,,,,,

0.88

::::::::

0.84

,,,,

0.81

::::

0.75

taboola

0.72

tel

0.72

then

0.71

tra

0.69

;;;;;;;;;;;;

0.68

Lad

0.66

Activations Density 0.030%

phrases and words related to email promotions

instances of punctuation and formatting in writing

No Comments

No Known Activations