INDEX

Explanations

legal and governmental terms and entities

oai_token-act-pair · gpt-3.5-turbo

references to regulatory or financial terms and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 thor

-0.55

thro

-0.54

 wiser

-0.54

 unused

-0.51

 planes

-0.51

psy

-0.50

stro

-0.50

 biome

-0.49

 throats

-0.47

xus

-0.47

POSITIVE LOGITS

ONSORED

0.66

æĸ¹

0.62

ahime

0.59

ãĥ¼ãĥ«

0.58

 Samoa

0.58

ĨĴ

0.57

 Tanzania

0.55

0.54

heit

0.54

ãĥı

0.53

Activations Density 1.014%

legal and governmental terms and entities

references to regulatory or financial terms and statistics

No Comments

No Known Activations