INDEX

Explanations

phrases related to influence, impact, or significance

oai_token-act-pair · gpt-3.5-turbo

active verbs that indicate significant actions or changes

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

 situ

-0.61

 prow

-0.57

 Adventure

-0.56

 fuss

-0.53

 Classes

-0.52

 humanoid

-0.52

 Bard

-0.52

sul

-0.52

 Mondays

-0.51

 Paula

-0.51

POSITIVE LOGITS

quickShipAvailable

0.90

soType

0.79

ï¸

0.78

vind

0.69

uates

0.68

ĺħ

0.68

 discredit

0.65

CVE

0.64

 deterrence

0.64

 outwe

0.64

Activations Density 0.315%

phrases related to influence, impact, or significance

active verbs that indicate significant actions or changes

No Comments

No Known Activations