INDEX

Explanations

words that end with the suffix '-ably' with a focus on those that have high relevance

oai_token-act-pair · gpt-3.5-turbo

adverbs that describe capability or manner

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

ongyang

-0.78

ancial

-0.72

itu

-0.69

cffff

-0.68

icip

-0.68

escription

-0.67

utenberg

-0.67

raltar

-0.67

sters

-0.66

sonian

-0.66

POSITIVE LOGITS

idis

0.72

jured

0.71

 disposed

0.71

ãĤ©

0.70

ffe

0.69

ãĤ´ãĥ³

0.65

 foreseeable

0.65

âĶĢâĶĢ

0.64

gged

0.63

\\\\

0.63

Activations Density 0.027%

words that end with the suffix '-ably' with a focus on those that have high relevance

adverbs that describe capability or manner

No Comments

No Known Activations