INDEX

Explanations

references to the speaker or writer within the text

oai_token-act-pair · gpt-3.5-turbo

the repeated use of the word "myself."

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

heny

-0.79

*/(

-0.78

rought

-0.77

olid

-0.76

ories

-0.69

origin

-0.65

iens

-0.65

Delivery

-0.64

cemic

-0.63

oons

-0.63

POSITIVE LOGITS

ħĭ

0.70

 personally

0.69

 confess

0.68

 myself

0.67

 creatively

0.67

uckland

0.67

odox

0.66

imei

0.66

selves

0.65

 profess

0.64

Activations Density 0.027%

references to the speaker or writer within the text

the repeated use of the word "myself."

No Comments

No Known Activations