INDEX

Explanations

words related to organizations, specifically names and terms related to specific organizations or institutions

oai_token-act-pair · gpt-3.5-turbo

references to organizations and institutional frameworks

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

seless

-0.70

jri

-0.66

hester

-0.61

isSpecialOrderable

-0.61

achine

-0.60

theless

-0.52

anwhile

-0.52

accompan

-0.52

ramid

-0.51

ipeg

-0.51

POSITIVE LOGITS

 Gleaming

0.58

gypt

0.56

Oo

0.55

ende

0.54

 Mormonism

0.54

 Architecture

0.52

è£ħ

0.52

 Manga

0.52

 leaps

0.51

 SOLD

0.50

Activations Density 1.167%

words related to organizations, specifically names and terms related to specific organizations or institutions

references to organizations and institutional frameworks

No Comments

No Known Activations