INDEX

Explanations

phrases indicating the speaker is emphasizing a particular statement

oai_token-act-pair · gpt-3.5-turbo

expressions of assertion or declaration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Flavoring

-0.81

ickets

-0.74

isal

-0.70

oder

-0.69

ento

-0.67

iana

-0.67

kson

-0.66

osate

-0.66

 ..........

-0.66

aspberry

-0.66

POSITIVE LOGITS

 kidding

0.85

 understatement

0.75

 coinc

0.67

 plural

0.66

 typo

0.66

 initials

0.64

 spoilers

0.63

 anecdotal

0.63

 countdown

0.62

\"

0.62

Activations Density 0.140%

phrases indicating the speaker is emphasizing a particular statement

expressions of assertion or declaration

No Comments

No Known Activations