INDEX

Explanations

words related to contrast or exception within a context

oai_token-act-pair · gpt-3.5-turbo

conjunctions and transitional phrases indicating contrast or exception

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

ether

-0.79

ixel

-0.66

orthy

-0.64

rez

-0.63

Sharp

-0.63

IFE

-0.62

bright

-0.60

SPA

-0.60

Els

-0.60

aepernick

-0.60

POSITIVE LOGITS

 streng

0.82

pires

0.77

etheless

0.74

vo

0.70

 occas

0.69

ĪĴ

0.68

ptr

0.67

ãĤ©

0.65

 cannabin

0.61

 confir

0.61

Activations Density 0.280%

words related to contrast or exception within a context

conjunctions and transitional phrases indicating contrast or exception

No Comments

No Known Activations